# Table of Contents

- [Deepgram API Overview | Deepgram's Docs](#deepgram-api-overview-deepgram-s-docs)
- [Welcome to Deepgram's Docs! | Deepgram's Docs](#welcome-to-deepgram-s-docs-deepgram-s-docs)
- [Changelog | Deepgram's Docs](#changelog-deepgram-s-docs)
- [Support | Deepgram's Docs](#support-deepgram-s-docs)
- [August 6, 2025 | Deepgram's Docs](#august-6-2025-deepgram-s-docs)
- [September 4, 2025 | Deepgram's Docs](#september-4-2025-deepgram-s-docs)
- [October 16, 2025 | Deepgram's Docs](#october-16-2025-deepgram-s-docs)
- [September 2, 2025 | Deepgram's Docs](#september-2-2025-deepgram-s-docs)
- [October 2, 2025 | Deepgram's Docs](#october-2-2025-deepgram-s-docs)
- [August 8, 2025 | Deepgram's Docs](#august-8-2025-deepgram-s-docs)
- [September 16, 2025 | Deepgram's Docs](#september-16-2025-deepgram-s-docs)
- [July 31, 2025 | Deepgram's Docs](#july-31-2025-deepgram-s-docs)
- [July 11, 2025 | Deepgram's Docs](#july-11-2025-deepgram-s-docs)
- [Voice Agent | Deepgram's Docs](#voice-agent-deepgram-s-docs)
- [March 31, 2025 | Deepgram's Docs](#march-31-2025-deepgram-s-docs)
- [March 11, 2025 | Deepgram's Docs](#march-11-2025-deepgram-s-docs)
- [May 21, 2025 | Deepgram's Docs](#may-21-2025-deepgram-s-docs)
- [September 12, 2024 | Deepgram's Docs](#september-12-2024-deepgram-s-docs)
- [August 15, 2025 | Deepgram's Docs](#august-15-2025-deepgram-s-docs)
- [March 3, 2025 | Deepgram's Docs](#march-3-2025-deepgram-s-docs)
- [December 16, 2024 | Deepgram's Docs](#december-16-2024-deepgram-s-docs)
- [June 11, 2025 | Deepgram's Docs](#june-11-2025-deepgram-s-docs)
- [February 12, 2025 | Deepgram's Docs](#february-12-2025-deepgram-s-docs)
- [April 2, 2025 | Deepgram's Docs](#april-2-2025-deepgram-s-docs)
- [August 19, 2024 | Deepgram's Docs](#august-19-2024-deepgram-s-docs)
- [August 15, 2024 | Deepgram's Docs](#august-15-2024-deepgram-s-docs)
- [Speech-to-Text | Deepgram's Docs](#speech-to-text-deepgram-s-docs)
- [July 22, 2024 | Deepgram's Docs](#july-22-2024-deepgram-s-docs)
- [September 28, 2023 | Deepgram's Docs](#september-28-2023-deepgram-s-docs)
- [June 2, 2023 | Deepgram's Docs](#june-2-2023-deepgram-s-docs)
- [May 24, 2024 | Deepgram's Docs](#may-24-2024-deepgram-s-docs)
- [May 11, 2023 | Deepgram's Docs](#may-11-2023-deepgram-s-docs)
- [July 16, 2024 | Deepgram's Docs](#july-16-2024-deepgram-s-docs)
- [June 30, 2023 | Deepgram's Docs](#june-30-2023-deepgram-s-docs)
- [October 17, 2022 | Deepgram's Docs](#october-17-2022-deepgram-s-docs)
- [March 15, 2023 | Deepgram's Docs](#march-15-2023-deepgram-s-docs)
- [February 27, 2023 | Deepgram's Docs](#february-27-2023-deepgram-s-docs)
- [October 14, 2022 | Deepgram's Docs](#october-14-2022-deepgram-s-docs)
- [April 13, 2023 | Deepgram's Docs](#april-13-2023-deepgram-s-docs)

---

# Deepgram API Overview | Deepgram's Docs

Deepgram’s APIs allows you to interact with Deepgram programmatically. You can use our APIs to:

*   Build a [Voice Agent](https://developers.deepgram.com/reference/voice-agent/agent)
    
*   Transcribe [streaming audio](https://developers.deepgram.com/reference/speech-to-text/listen-streaming)
    
*   Transcribe & analyze [pre-recorded audio](https://developers.deepgram.com/reference/speech-to-text/transcribe)
    
*   Transcribe [turn-based audio](https://developers.deepgram.com/reference/speech-to-text/listen-flux)
    
*   Transform a [continuous text stream](https://developers.deepgram.com/reference/text-to-speech/speak-streaming)
    
*   Transform a [single text request](https://developers.deepgram.com/reference/text-to-speech/generate)
    
*   Analyze [text](https://developers.deepgram.com/reference/text-intelligence/analyze)
    
*   Get all available [Deepgram models](https://developers.deepgram.com/reference/manage/models/list)
    
*   Get [model metadata](https://developers.deepgram.com/reference/manage/models/get)
    
*   Create [Temporary API Tokens](https://developers.deepgram.com/reference/auth/tokens/grant)
    
*   Administer your Deepgram account:
    
    *   Manage [projects](https://developers.deepgram.com/reference/manage/projects/list)
         and project [members](https://developers.deepgram.com/reference/manage/members/list)
        
    *   Manage project [invitations](https://developers.deepgram.com/reference/manage/invites/list)
        
    *   Manage user [scopes](https://developers.deepgram.com/reference/manage/members/scopes/list)
        
    *   Get billing [balances](https://developers.deepgram.com/reference/manage/balances/list)
        
    *   Get billing [usage breakdown](https://developers.deepgram.com/reference/manage/usage/breakdown/get)
        
    *   Get project [requests](https://developers.deepgram.com/reference/manage/requests/list)
        
    *   Manage [API keys](https://developers.deepgram.com/reference/manage/keys/list)
        
    *   Manage [self-hosted distribution credentials](https://developers.deepgram.com/reference/self-hosted/distribution-credentials/list)
        

  

To create your first API key refer to our Guide [Creating API Keys](https://developers.deepgram.com/docs/create-additional-api-keys)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# Welcome to Deepgram's Docs! | Deepgram's Docs

[Introducing Flux, the first conversational speech recognition model built for voice agents.](https://developers.deepgram.com/docs/flux/quickstart)

Build with Deepgram
-------------------

Voice Agents

[End to end Voice Agent API](https://developers.deepgram.com/docs/voice-agent)

[Chain LLMs with STT and TTS APIs](https://developers.deepgram.com/docs/flux/agent)

Speech to Text

[Streaming: Conversational STT for voice agents (Flux)](https://developers.deepgram.com/docs/flux/quickstart)

[Streaming: Transcription (Nova-3)](https://developers.deepgram.com/docs/live-streaming-audio)

[Pre-recorded audio](https://developers.deepgram.com/docs/pre-recorded-audio)

[Models and languages](https://developers.deepgram.com/docs/models-languages-overview)

Text to Speech

[Single Text Request](https://developers.deepgram.com/docs/text-to-speech)

[Continuous Text Stream](https://developers.deepgram.com/docs/streaming-text-to-speech)

[Voices and Languages](https://developers.deepgram.com/docs/tts-models)

SDKs
----

[![Python](https://fern-image-hosting.s3.us-east-1.amazonaws.com/deepgram/python.svg)\
\
Python SDK](https://github.com/deepgram/deepgram-python-sdk)
[![JavaScript](https://fern-image-hosting.s3.us-east-1.amazonaws.com/deepgram/js-yellow.svg)\
\
JS SDK](https://github.com/deepgram/deepgram-js-sdk/)
[![Go](https://fern-image-hosting.s3.us-east-1.amazonaws.com/deepgram/go.svg)\
\
Go SDK](https://github.com/deepgram/deepgram-go-sdk)
[![.NET](https://fern-image-hosting.s3.us-east-1.amazonaws.com/deepgram/net.svg)\
\
.NET SDK](https://github.com/deepgram/deepgram-dotnet-sdk)

Resources
---------

Explore

[Playground](https://playground.deepgram.com/)

[API Reference](https://developers.deepgram.com/reference/deepgram-api-overview)

Self-Host

[Get started: Self Hosted](https://developers.deepgram.com/docs/self-hosted-introduction)

[Self Hosted Add-Ons](https://developers.deepgram.com/docs/self-hosted-add-ons)

Community

[Discord](https://dpgr.am/discord)

[Discussions Forums](https://github.com/orgs/deepgram/discussions)

Trust & Safety

[Security](https://developers.deepgram.com/docs/security-policy)

[Compliance](https://developers.deepgram.com/docs/data-privacy-compliance)

[Privacy](https://developers.deepgram.com/docs/information-security-privacy-statement)

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# Changelog | Deepgram's Docs

Check out our changelog.

*   [Voice Agent](https://developers.deepgram.com/changelog/voice-agent-changelog)
    
*   [Speech-to-Text](https://developers.deepgram.com/changelog/speech-to-text-changelog)
    
*   [Text-to-Speech](https://developers.deepgram.com/changelog/text-to-speech-changelog)
    
*   [Saga](https://developers.deepgram.com/changelog/saga-changelog)
    
*   [Developer Tools](https://developers.deepgram.com/changelog/developer-tools-changelog)
    
*   [Self Hosted](https://developers.deepgram.com/changelog/self-hosted-changelog)
    
*   [Deepgram Dedicated](https://developers.deepgram.com/changelog/deepgram-dedicated-changelog)
    
*   [Intelligence](https://developers.deepgram.com/changelog/intelligence-changelog)
    

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# Support | Deepgram's Docs

Deepgram Community
------------------

*   [Deepgram Discord](https://dpgr.am/discord)
    
*   [Deepgram Discussions Forum](https://github.com/orgs/deepgram/discussions)
    
*   [Deepgram Code of Conduct](https://developers.deepgram.com/code-of-conduct)
    

Support Plans
-------------

If your organization has a contracted Premium or VIP Support Plan, please contact Deepgram Support; otherwise, visit our Community or GitHub Discussions for assistance.

![Deepgram Support](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/images/529aca7-dg_support_image.svg)

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# August 6, 2025 | Deepgram's Docs

[August 6, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/8/6)

Voice Agent API
---------------

### New Features

#### 🤖 GPT-OSS-20B LLM Support

We’ve added support for OpenAI’s first open source LLM, gpt-oss-20b, in our Voice Agent API!

**Available Models:**

*   GPT OSS 20B

**Implementation:** Configure GPT-OSS-20B in your Voice Agent settings:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "Settings", | | 3   | "agent": { | | 4   | "think": { | | 5   | "provider": { | | 6   | "type": "groq", | | 7   | "model": "openai/gpt-oss-20b" | | 8   | }   | | 9   | }   | | 10  | }   | | 11  | }   |     `

For complete information about supported LLMs including GPT OSS 20B, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models#openai)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# September 4, 2025 | Deepgram's Docs

[September 4, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/9/4)

Increased Voice Agent Rate Limits for Pay as you Go and Growth Plans
--------------------------------------------------------------------

Deepgram is excited to announce **3x increased rate limits** for Voice Agent services on Pay-as-You-Go and Growth plans, enabling higher concurrent usage for your applications at no additional charge.

For detailed information about all rate limits, please refer to our [API Rate Limits documentation](https://developers.deepgram.com/reference/api-rate-limits)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# October 16, 2025 | Deepgram's Docs

[October 16, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/10/16)

Flux: Expanded Audio Format Support
-----------------------------------

Flux now supports a wider range of audio formats beyond `linear16`, giving you more flexibility in how you send audio to our conversational speech recognition model. This update adds support for additional raw audio encodings and containerized audio formats.

### Raw Audio Format Support

Flux now accepts the following raw (non-containerized) audio encodings:

*   `linear16` - 16-bit signed little-endian PCM (existing)
*   `linear32` - 32-bit signed little-endian PCM (new)
*   `mulaw` - Mu-law encoding (new)
*   `alaw` - A-law encoding (new)
*   `opus` - Opus codec (new)
*   `ogg-opus` - Opus in Ogg container (new)

When using raw audio formats, you must specify both the `encoding` and `sample_rate` parameters in your API request.

### Containerized Audio Support

Flux now also accepts containerized audio formats, eliminating the need to manually specify encoding and sample rate parameters:

*   **WAV containers** with `linear16` encoding
*   **Ogg containers** with `opus` encoding

When sending containerized audio, **omit** the `encoding` and `sample_rate` parameters—Flux will automatically detect these from the container metadata.

### Supported Sample Rates

For raw audio, Flux supports the following sample rates:

*   8000 Hz
*   16000 Hz (recommended)
*   24000 Hz
*   44100 Hz
*   48000 Hz

### Implementation

**For raw audio:**

`   wss://api.deepgram.com/v2/listen?model=flux-general-en&encoding=linear16&sample_rate=16000   `

**For containerized audio:**

`   wss://api.deepgram.com/v2/listen?model=flux-general-en   `

For detailed information about Flux audio requirements, see our [Flux documentation](https://developers.deepgram.com/docs/flux/quickstart)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# September 2, 2025 | Deepgram's Docs

[September 2, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/9/2)

Nova-3 Model Update
-------------------

#### 🎯 Nova-3 supports 3 new languages

We’ve added support for 3 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 language support beyond English. The newly supported languages and their corresponding language codes are:

**Newly Supported:**

*   Spanish (`es`, `es-419`)
*   French (`fr`, `fr-CA`)
*   Portuguese (`pt`, `pt-BR`, `pt-PT`)

Learn more about Nova-3 on the [Models and Language Overview](https://developers.deepgram.com/docs/models-languages-overview)
 page.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# October 2, 2025 | Deepgram's Docs

[October 2, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/10/2)

Introducing Flux: Conversational Speech Recognition to Solve the Biggest Problem in Voice Agents – Interruptions
----------------------------------------------------------------------------------------------------------------

#### Flux is here: the first real-time Conversational Speech Recognition model built for voice agents. Solve interruptions, cut latency, and ship natural conversations faster than ever.

Deepgram is proud to announce the release of [Flux](https://deepgram.com/learn/introducing-flux-conversational-speech-recognition)
, the first speech recognition model that knows when someone is actually done talking. Built for conversation, not transcription.

**Key Features:**

*   **Model-integrated turn detection** that understands context and conversation flow, not just silence
*   **Ultra-low latency when it matters most** - transcripts that are ready as soon as turns end
*   **Nova-3 level transcription quality** - high-quality speech-to-text (STT) that’s every bit as accurate as the best models, including keyterm prompting
*   **Radically simpler development** - one API replaces complex STT+VAD+endpointing pipelines, and conversation-native events designed to make voice agent development a breeze
*   **Configurability for your use case** - the right amount of complexity, allowing developers to achieve the desired behavior for their agent

**Use Cases:**

Designed for real-time conversational applications: voice agents, AI assistants, IVR systems, and any application requiring natural dialogue flow. For pure transcription (meetings, captions, recordings), continue using Nova-3.

**Getting Started:**

Flux is **free throughout October 2025** for our OktoberFLUX promotion (up to 50 concurrent connections). Use `model=flux-general-en` via the new `/v2/listen` endpoint.

Learn more in our [Announcement Blog](https://deepgram.com/learn/introducing-flux-conversational-speech-recognition)
, [Developer Documentation](https://developers.deepgram.com/docs/flux/quickstart)
, [API Reference](https://developers.deepgram.com/reference/speech-to-text/listen-flux)
, and try the [Interactive Demo](https://flux.deepgram.com/)
.

### Availability

Flux English is now available through our API. To access:

*   Connect to `wss://api.deepgram.com/v2/listen` using `model=flux-general-en` (reference additional [required params here](https://developers.deepgram.com/reference/speech-to-text/listen-flux)
    
*   Available for hosted use
*   Real-time streaming only
*   Self-hosted support coming soon
*   English-only for now

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# August 8, 2025 | Deepgram's Docs

[August 8, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/8/8)

Voice Agent API
---------------

### New Features

#### 🤖 GPT 5.0 LLM Support

We’ve added support for OpenAI’s new 5.0 models in our Voice Agent API!

**Available Models:**

*   5.0 (gpt-5)
*   5.0 Mini (gpt-5-mini)
*   5.0 Nano (gpt-5-nano)

**Implementation:** Configure your chosen model in your Voice Agent settings:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "Settings", | | 3   | "agent": { | | 4   | "think": { | | 5   | "provider": { | | 6   | "type": "open_ai", | | 7   | "model": "gpt-5" | | 8   | }   | | 9   | }   | | 10  | }   | | 11  | }   |     `

For complete information about supported LLMs including the GPT 5.0 models, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models#openai)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# September 16, 2025 | Deepgram's Docs

[September 16, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/9/16)

Nova-3 Model Update
-------------------

#### 🎯 Nova-3 supports 4 new languages

We’ve added support for 4 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 language support beyond English. The newly supported languages and their corresponding language codes are:

**Newly Supported:**

*   Italian (`it`)
*   Turkish (`tr`)
*   Norwegian (`no`)
*   Indonesian (`id`)

Learn more about Nova-3 on the [Models and Language Overview](https://developers.deepgram.com/docs/models-languages-overview)
 page.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# July 31, 2025 | Deepgram's Docs

[July 31, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/7/31)

Voice Agent API
---------------

### New Features

#### 🎯 Smart Formatting for More Readable Conversations

We’ve added a new `smart_format` option to improve transcript readability in UI applications. This feature enables smart formatting for better user experience when displaying transcribed conversation.

**Key Features:**

*   Enhanced transcript formatting for UI applications
*   Defaults to `false` for backward compatibility

**Implementation:** Configure the `smart_format` option in your Voice Agent listen provider settings:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "agent": { | | 3   | "listen": { | | 4   | "provider": { | | 5   | "type": "deepgram", | | 6   | "model": "nova-3", | | 7   | "smart_format": true | | 8   | }   | | 9   | }   | | 10  | }   | | 11  | }   |     `

For complete implementation details, see our [Voice Agent configuration documentation](https://developers.deepgram.com/docs/configure-voice-agent)
.

#### 🔒 Model Improvement Program Opt-Out

Users can now opt out of our Model Improvement Program when using the Voice Agent API.

**Implementation:** Add `mip_opt_out: true` to your Settings message:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "Settings", | | 3   | "mip_opt_out": true, | | 4   | "agent": { | | 5   | "listen": { | | 6   | "provider": { | | 7   | "type": "deepgram", | | 8   | "model": "nova-3" | | 9   | }   | | 10  | }   | | 11  | }   | | 12  | }   |     `

For more information about the Model Improvement Program and opt-out options, visit our [Model Improvement Partnership Program documentation](https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#voice-agent-example)
.

#### 🤖 Gemini LLM Support

We’ve added support for Google’s Gemini LLMs in our Voice Agent API! This expands our LLM options to include Google’s powerful language models.

**Available Models:**

*   Gemini 2.5 Flash
*   Gemini 2.0 Flash
*   Gemini 2.0 Flash Lite

For complete information about supported LLMs including Gemini models, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models#google)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# July 11, 2025 | Deepgram's Docs

[July 11, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/7/11)

Voice Agent API
---------------

### New Features

#### 🤖 Expanded LLM Support

We’ve significantly expanded our LLM options across our two pricing tiers. The following LLMs are now available for use:

**Standard Models**

*   OpenAI GPT-4.1 mini
*   OpenAI GPT-4.1 nano
*   OpenAI GPT-4o mini
*   Anthropic Claude Haiku 3.5

**Advanced Models**

*   OpenAI GPT-4.1
*   OpenAI GPT-4o
*   Anthropic Claude Sonnet 4

For complete information about supported LLMs, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models)
 or try them out in our [API Playground](https://playground.deepgram.com/?endpoint=agent)
.

#### 🌍 Spanish Language Support

Voice Agents now support Spanish conversations with the addition of Aura-2 Spanish TTS. Configure your agent’s language settings to enable Spanish voice interactions.

See our [Voice Agent API documentation](https://developers.deepgram.com/reference/voice-agent-api/agent#send.sendSettings.agent.language)
 for implementation details.

#### 💬 Conversation Context Feature

Introducing comprehensive conversation continuity with our new context feature:

**Complete Context Awareness**

*   Agents maintain conversation history across sessions
*   Seamless continuation of previous interactions

**Enhanced User Experience**

*   More natural conversations with historical context
*   Consistent interaction patterns across sessions

**Flexible Implementation**

*   Support for both conversational and function call history
*   Configurable history settings

##### Implementation

Use the `agent.context` object to provide conversation history when starting new sessions:

**Conversational Messages:**

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "History", | | 3   | "role": "user" \| "assistant", | | 4   | "content": "message text" | | 5   | }   |     `

**Function Call Messages:**

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "History", | | 3   | "function_calls": [{ | | 4   | "id": "unique_id", | | 5   | "name": "function_name", | | 6   | "client_side": true/false, | | 7   | "arguments": "json_string", | | 8   | "response": "response_text" | | 9   | }]  | | 10  | }   |     `

To disable function call history, set `settings.flags.history` to `false` in the Settings message.

Documentation

*   [Configure Voice Agent Context](https://developers.deepgram.com/docs/configure-voice-agent#agentcontext)
    

#### 🔍 Enhanced Error Visibility

We’ve improved client-side visibility of LLM and TTS errors to provide better debugging and user experience.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# Voice Agent | Deepgram's Docs

[September 4, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/9/4)

Increased Voice Agent Rate Limits for Pay as you Go and Growth Plans
--------------------------------------------------------------------

Deepgram is excited to announce **3x increased rate limits** for Voice Agent services on Pay-as-You-Go and Growth plans, enabling higher concurrent usage for your applications at no additional charge.

For detailed information about all rate limits, please refer to our [API Rate Limits documentation](https://developers.deepgram.com/reference/api-rate-limits)
.

* * *

[August 8, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/8/8)

Voice Agent API
---------------

### New Features

#### 🤖 GPT 5.0 LLM Support

We’ve added support for OpenAI’s new 5.0 models in our Voice Agent API!

**Available Models:**

*   5.0 (gpt-5)
*   5.0 Mini (gpt-5-mini)
*   5.0 Nano (gpt-5-nano)

**Implementation:** Configure your chosen model in your Voice Agent settings:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "Settings", | | 3   | "agent": { | | 4   | "think": { | | 5   | "provider": { | | 6   | "type": "open_ai", | | 7   | "model": "gpt-5" | | 8   | }   | | 9   | }   | | 10  | }   | | 11  | }   |     `

For complete information about supported LLMs including the GPT 5.0 models, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models#openai)
.

* * *

[August 6, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/8/6)

Voice Agent API
---------------

### New Features

#### 🤖 GPT-OSS-20B LLM Support

We’ve added support for OpenAI’s first open source LLM, gpt-oss-20b, in our Voice Agent API!

**Available Models:**

*   GPT OSS 20B

**Implementation:** Configure GPT-OSS-20B in your Voice Agent settings:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "Settings", | | 3   | "agent": { | | 4   | "think": { | | 5   | "provider": { | | 6   | "type": "groq", | | 7   | "model": "openai/gpt-oss-20b" | | 8   | }   | | 9   | }   | | 10  | }   | | 11  | }   |     `

For complete information about supported LLMs including GPT OSS 20B, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models#openai)
.

* * *

[July 31, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/7/31)

Voice Agent API
---------------

### New Features

#### 🎯 Smart Formatting for More Readable Conversations

We’ve added a new `smart_format` option to improve transcript readability in UI applications. This feature enables smart formatting for better user experience when displaying transcribed conversation.

**Key Features:**

*   Enhanced transcript formatting for UI applications
*   Defaults to `false` for backward compatibility

**Implementation:** Configure the `smart_format` option in your Voice Agent listen provider settings:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "agent": { | | 3   | "listen": { | | 4   | "provider": { | | 5   | "type": "deepgram", | | 6   | "model": "nova-3", | | 7   | "smart_format": true | | 8   | }   | | 9   | }   | | 10  | }   | | 11  | }   |     `

For complete implementation details, see our [Voice Agent configuration documentation](https://developers.deepgram.com/docs/configure-voice-agent)
.

#### 🔒 Model Improvement Program Opt-Out

Users can now opt out of our Model Improvement Program when using the Voice Agent API.

**Implementation:** Add `mip_opt_out: true` to your Settings message:

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "Settings", | | 3   | "mip_opt_out": true, | | 4   | "agent": { | | 5   | "listen": { | | 6   | "provider": { | | 7   | "type": "deepgram", | | 8   | "model": "nova-3" | | 9   | }   | | 10  | }   | | 11  | }   | | 12  | }   |     `

For more information about the Model Improvement Program and opt-out options, visit our [Model Improvement Partnership Program documentation](https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#voice-agent-example)
.

#### 🤖 Gemini LLM Support

We’ve added support for Google’s Gemini LLMs in our Voice Agent API! This expands our LLM options to include Google’s powerful language models.

**Available Models:**

*   Gemini 2.5 Flash
*   Gemini 2.0 Flash
*   Gemini 2.0 Flash Lite

For complete information about supported LLMs including Gemini models, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models#google)
.

* * *

[July 11, 2025](https://developers.deepgram.com/changelog/voice-agent-changelog/2025/7/11)

Voice Agent API
---------------

### New Features

#### 🤖 Expanded LLM Support

We’ve significantly expanded our LLM options across our two pricing tiers. The following LLMs are now available for use:

**Standard Models**

*   OpenAI GPT-4.1 mini
*   OpenAI GPT-4.1 nano
*   OpenAI GPT-4o mini
*   Anthropic Claude Haiku 3.5

**Advanced Models**

*   OpenAI GPT-4.1
*   OpenAI GPT-4o
*   Anthropic Claude Sonnet 4

For complete information about supported LLMs, visit our [Voice Agent LLM Models documentation](https://developers.deepgram.com/docs/voice-agent-llm-models)
 or try them out in our [API Playground](https://playground.deepgram.com/?endpoint=agent)
.

#### 🌍 Spanish Language Support

Voice Agents now support Spanish conversations with the addition of Aura-2 Spanish TTS. Configure your agent’s language settings to enable Spanish voice interactions.

See our [Voice Agent API documentation](https://developers.deepgram.com/reference/voice-agent-api/agent#send.sendSettings.agent.language)
 for implementation details.

#### 💬 Conversation Context Feature

Introducing comprehensive conversation continuity with our new context feature:

**Complete Context Awareness**

*   Agents maintain conversation history across sessions
*   Seamless continuation of previous interactions

**Enhanced User Experience**

*   More natural conversations with historical context
*   Consistent interaction patterns across sessions

**Flexible Implementation**

*   Support for both conversational and function call history
*   Configurable history settings

##### Implementation

Use the `agent.context` object to provide conversation history when starting new sessions:

**Conversational Messages:**

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "History", | | 3   | "role": "user" \| "assistant", | | 4   | "content": "message text" | | 5   | }   |     `

**Function Call Messages:**

`   |     |     | | --- | --- | | 1   | {   | | 2   | "type": "History", | | 3   | "function_calls": [{ | | 4   | "id": "unique_id", | | 5   | "name": "function_name", | | 6   | "client_side": true/false, | | 7   | "arguments": "json_string", | | 8   | "response": "response_text" | | 9   | }]  | | 10  | }   |     `

To disable function call history, set `settings.flags.history` to `false` in the Settings message.

Documentation

*   [Configure Voice Agent Context](https://developers.deepgram.com/docs/configure-voice-agent#agentcontext)
    

#### 🔍 Enhanced Error Visibility

We’ve improved client-side visibility of LLM and TTS errors to provide better debugging and user experience.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# March 31, 2025 | Deepgram's Docs

[March 31, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/3/31)

Nova-3 Multilingual General Availability - Real-Time Code-Switching
-------------------------------------------------------------------

Deepgram is proud to announce the general availability of Nova-3 Multilingual, the first model of its kind able to codeswitch in real-time across 10 different languages. This revolutionary capability unlocks a host of new possibilities for global operations by processing multilingual conversations instantly with a single model—an industry-first breakthrough that changes the game for speech recognition.

### Multilingual Support

*   **Real-time multilingual speech recognition** with a truly unified speech recognition system
    
*   Supports code-switching between 10 languages:
    
    *   English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch
*   Seamlessly handles natural language transitions without relying on explicit routing or language-specific mechanisms
    
*   Maintains high transcription accuracy across languages while adapting to natural language transitions
    
*   Developed through a multi-stage training process combining synthetic code-switched data at massive scale with carefully curated real-world datasets
    

### Use Cases

Nova-3 Multilingual represents a significant breakthrough for applications in:

*   Global customer support
*   Emergency response (e.g., 911 calls)
*   Multilingual meetings
*   Retail interactions
*   Healthcare settings

In high-stakes scenarios like emergency response, Nova-3 can fluidly process interactions where callers switch between languages (e.g., Spanish and English) in real time, ensuring dispatchers receive accurate, immediate transcriptions without missing critical details.

### Availability

*   Now available through our API
*   Use `model=nova-3&language=multi` in your API calls
*   Supports both pre-recorded and real-time streaming transcription
*   Available for hosted and self-hosted use

For detailed information about Nova-3 Multilingual, please refer to our [Developer Documentation](https://developers.deepgram.com/docs/multilingual-code-switching)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# March 11, 2025 | Deepgram's Docs

[March 11, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/3/11)

Expanded Numerals Language Support
----------------------------------

Deepgram is excited to announce expanded language support for numerals through our `numerals` and `smart_format` parameters, providing more comprehensive coverage for converting written numbers to numerical format across additional languages.

### Expanded Language Support

*   **New languages added to Numerals support:**
    *   Danish: `da`, `da-DK`
    *   Dutch: `nl`
    *   French: `fr`, `fr-CA`
    *   German: `de`
    *   German (Switzerland): `de-CH`
    *   Italian: `it`
    *   Norwegian: `no`
    *   Polish: `pl`
    *   Portuguese: `pt`, `pt-BR`, `pt-PT`
    *   Spanish: `es`, `es-419`
    *   Swedish: `sv`, `sv-SE`

**Previously supported language:**

*   English: `en`, `en-US`, `en-AU`, `en-GB`, `en-NZ`, `en-IN`

### Feature Integration

*   All newly supported languages are fully integrated with our Smart Format feature
*   When using `smart_format=true`, numerals will automatically be applied for all supported languages
*   Individual control remains available through the dedicated `numerals=true` parameter

### Availability

The expanded Numerals support is now available through our API for use with all Deepgram speech-to-text models.

*   Available for hosted and self-hosted usage.
*   Compatible with both pre-recorded and real-time streaming transcription

For detailed information about our expanded [Numerals](https://deepgram-preview-e9e61f4a-067d-48e1-9981-892b671eaaf8.docs.buildwithfern.com/docs/numerals)
 or [Smart Formatting](https://deepgram-preview-e9e61f4a-067d-48e1-9981-892b671eaaf8.docs.buildwithfern.com/docs/smart-format)
 support, please refer to our Developer Documentation.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# May 21, 2025 | Deepgram's Docs

[May 21, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/5/21)

Nova-3 Medical Streaming Significant Upgrade
--------------------------------------------

We’ve just released a significant upgrade to **Nova-3 Medical Streaming**, bringing substantial improvements in accuracy for real-time medical transcription use cases. This update focuses specifically on our **streaming model**, delivering better performance across key transcription metrics.

### Performance Improvements

*   \*\*11% relative reduction in Overall WER \*\*compared to Nova-3 general streaming model
*   \*\*30% relative reduction in Overall WER \*\*compared to Nova-2 Medical streaming model
*   \*\*2.7x improvement in Keyword Recall Rate (KRR) \*\*compared to Nova-3 general streaming model
*   Maintains industry-leading inference speed with ultra-low latency for real-time healthcare applications

### Availability

The updated Nova-3 Medical streaming model is now available through our API. To access:

*   Use `model=nova-3-medical` in your streaming API calls
*   Available for hosted use
*   Self-hosted deployments will be available in subsequent releases
*   English only

For details on the original Nova-3 Medical release (including batch capabilities), check out the original changelog: [Introducing Nova-3 Medical.](https://deepgram.com/changelog/introducing-nova-3-medical)
 For detailed information about Nova-3 Medical, please refer to our [Developer Documentation](https://developers.deepgram.com/docs/models-languages-overview#nova-3)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# September 12, 2024 | Deepgram's Docs

[September 12, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/9/12)

Nova-2 Cantonese Language Support
---------------------------------

`model=nova-2&language=zh-HK`

We’re excited to announce that we have released\*\* Cantonese support\*\* in our next-gen speech-to-text model, Nova-2.

See our [documentation](https://developers.deepgram.com/docs/models-languages-overview)
 for information.

For Self-Hosted customers, please reach out to your Deepgram contact if you’d like to use the new language.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# August 15, 2025 | Deepgram's Docs

[August 15, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/8/15)

Nova-3 Model Update
-------------------

#### 🎯 Nova-3 supports 4 new languages

We’ve added support for 4 new languages with non-English monolingual Nova-3 models. This is the beginning of an effort to significantly expand Nova-3 language support beyond English. The newly supported languages and their corresponding language codes are:

**Newly Supported:**

*   German (`de`)
*   Dutch (`nl`)
*   Swedish (`sv`, `sv-SE`)
*   Danish (`da`, `da-DK`)

Learn more about Nova-3 at [Models and Language Overview](https://developers.deepgram.com/docs/models-languages-overview)
 page

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# March 3, 2025 | Deepgram's Docs

[March 3, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/3/3)

Nova-3 Medical Model
--------------------

Deepgram is proud to announce the release of [Nova-3-Medical](https://deepgram.com/learn/introducing-nova-3-medical-speech-to-text-api)
, our most advanced speech-to-text model designed specifically for clinical environments. Built on the foundation of Nova-3, this specialized model delivers superior transcription performance for healthcare applications.

### Performance Improvements

*   63.7% reduction in word error rate (WER) compared to next-best competitor (3.44% median WER)
*   40.35% reduction in Keyword Error Rate (KER) compared to next-best competitor (6.79% KER)
*   10.6% improvement in Keyword Recall Rate (KRR) over Nova-2-Medical (93.99% KRR)
*   Maintains industry-leading inference speed with ultra-low latency for real-time healthcare applications

### New Features

*   Self-serve customization through [Keyterm Prompting](https://developers.deepgram.com/docs/keyterm)
    
    *   Instantly adapt up to 100 domain-specific terms without model retraining
*   Enhanced capabilities for clinical environments
    
    *   Improved handling of background noise typical in healthcare settings
    *   Superior recognition of medication names, diagnostic terms, and procedure details
    *   Accurate transcription even with far-field devices or ambient noise interference
    *   Maintains exceptional accuracy in bustling clinics or hospitals with active medical equipment

### Availability

Nova-3 English is now available through our API. To access:

*   Use `model=nova-3-medical` in your API calls
*   Available for hosted use
*   Supports both pre-recorded and real-time streaming transcription
*   Self-hosted deployments will be available in subsequent releases

For detailed information about Nova-3 Medical, please refer to our [Developer Documentation](https://developers.deepgram.com/docs/models-languages-overview#nova-3)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# December 16, 2024 | Deepgram's Docs

[December 16, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/12/16)

Enhanced Profanity Filtering System
-----------------------------------

### What’s New

The profanity filtering system (`profanity_filter=true`) now includes:

*   An expanded database of profane words and phrases
*   Real-time filtering support for streaming audio
*   Standardized asterisk replacement for filtered content

Note: Profanity Filtering is available for English-only.

### Key Changes

Previously, our system would replace detected profanity with similar-sounding words. With this update, all identified profane content is now consistently replaced with asterisks, providing clearer and more predictable output.

### Documentation & Support

*   See our [Profanity Filter documentation](https://developers.deepgram.com/docs/detect-entities)
     to learn more.
*   For Self-Hosted customers, please reach out to your Deepgram contact if you’d like to use the updated feature.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# June 11, 2025 | Deepgram's Docs

[June 11, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/6/11)

Profanity Filtering Expanded Language Support
---------------------------------------------

### Profanity Filtering Gets Expanded Language Support

Profanity filtering now supports **6 additional languages** beyond English, giving you content moderation capabilities across your global user base. Available on monolingual models for:

**Newly Supported:**

*   German (`de`)
*   Swiss German (`de-CH`)
*   Polish (`pl`)
*   Portuguese (`pt`, `pt-BR`, `pt-PT`)
*   Spanish (`es`, `es-419`)
*   Swedish (`sv`, `sv-SE`)

**Existing English Support:**

*   `en`, `en-US`, `en-AU`, `en-GB`, `en-NZ`, `en-IN`

This expansion lets you deploy consistent content policies across international markets without building custom filtering logic.

### Smart Formatting Improvements

We’ve resolved several high-impact formatting edge cases that were causing transcription accuracy issues in production environments:

### Improved Entity Formatting via Smart Format

**Email Transcription Improvements**

*   **Fixed:** `'o'` characters in email addresses now transcribe correctly instead of converting to `'0'`
*   **Fixed:** edge case email mentions that were being dropped entirely in specific batch processing scenarios

**Certain formerly numeric-only sequences have been updated to correctly preserve all alphanumeric characters:**

*   Before (some entities): `"my account number is a b c d zero nine"` → `"my account number is 09"`
*   After (some entities): `"my account number is a b c d zero nine"` → `"my account number is ABCD09"`

**Quantity modifiers (‘single’, ‘double’, ‘triple’ + standalone character or number) are better handled via Smart Format:**

*   Before (some entities): `"double 2"` → `"2"`
*   After (some entities): `"double 2"` → `"22"`

**Special cases of ‘hundred’ or ‘a hundred’ now supported via Smart Format:**

*   Before (some entities): `"hundred percent"` → `"%"`
*   After (some entities): `"hundred percent"` → `"100%"`

This update has gone out to all hosted streaming transcription, and will be applied to our next self-hosted release later this month.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# February 12, 2025 | Deepgram's Docs

[February 12, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/2/12)

Introducing Nova-3 - Most Advanced Speech-to-Text Model
-------------------------------------------------------

Deepgram is proud to announce the release of [Nova-3](https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)
, our most advanced speech-to-text model to date. Key improvements include:

### Performance Improvements

*   54.3% reduction in word error rate (WER) for streaming audio compared to competitors (6.84% median WER)
*   47.4% reduction in WER for batch processing (5.26% median WER)
*   Maintains industry-leading inference speed, with latency comparable to Nova-2

### New Features

*   Self-serve customization through [Keyterm Prompting](https://developers.deepgram.com/docs/keyterm)
    
    *   Instantly adapt up to 100 domain-specific terms without model retraining
    *   Improved recognition of specialized vocabulary and technical terminology
*   Enhanced capabilities for challenging audio conditions:
    
    *   Improved handling of background noise and overlapping speech
    *   Better numeric recognition
    *   Real-time redaction for up to 50 entities
    *   Greater word-level timestamp precision
    *   Improved English formatting and paragraph structuring

### Availability

Nova-3 English is now available through our API. To access:

*   Use `model=nova-3` in your API calls
*   Available for hosted use
*   Supports both pre-recorded and real-time streaming transcription
*   Multilingual and self-hosted deployments will be available in subsequent releases

For detailed information about Nova-3, please refer to our [Developer Documentation](https://developers.deepgram.com/docs/models-languages-overview#nova-3)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# April 2, 2025 | Deepgram's Docs

[April 2, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/4/2)

Smart Formatting Improvements
-----------------------------

We’ve made some improvements to Smart Formatting, enhancing both streaming finalization behavior and entity recognition performance.

### Streaming Finalization Improvements

Previously, when formatting entities like dates or credit card numbers, our models would sometimes wait for additional words before finalizing the transcript—particularly if the entity seemed incomplete. For example, when someone said “nineteen seventy…” Deepgram might pause, expecting a possible follow-up like “nine” or other additional speech before finalizing the complete year.

Now, instead of potentially waiting indefinitely for additional words, our system will finalize the transcript after **3 seconds of silence**, and attempt to format the entity based on the available audio. This helps ensure transcripts are returned faster and more reliably—without sacrificing too much formatting precision.

Want more control over the finalization behavior? You have two options:

*   Implement logic to send a `Finalize` message earlier than the 3-second threshold. Reference our [Finalize documentation](https://developers.deepgram.com/docs/finalize)
     here.
*   Set `no_delay=true` to override formatting and force immediate finalization. NOTE: This will result in skipping formatting altogether in many cases.

### Enhanced Entity Formatting

In addition to the timeout improvements, we’ve refined our [Named Entity Recognition](https://deepgram.com/ai-glossary/named-entity-recognition)
 model for Smart Formatting to better identify and format:

*   Date variations
*   Alphanumerics (order numbers, membership IDs, prescription numbers, etc.)
*   Currencies
*   Payment and card information
*   SSNs
*   Time zones

This update is automatically applied to all streaming transcription using Smart Formatting, and is included in our Self-Hosted March 2025 Release (250331). For more details, check out our [Smart Formatting documentation](https://developers.deepgram.com/docs/smart-format)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# August 19, 2024 | Deepgram's Docs

[August 19, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/8/19)

Nova-2 Air Traffic Control Model Release
----------------------------------------

`model=nova-2-atc`

We’re excited to announce that we have released a use case model for transcribing English \*\*air traffic control \*\*audio in our next-gen speech-to-text model, Nova-2.

With full pre-recorded and streaming capabilities, it’s optimized for noisy and jargon heavy air traffic control conversations.

See our [documentation](https://developers.deepgram.com/docs/models-languages-overview)
 for information.

For Self-Hosted customers, please reach out to your Deepgram contact if you’d like to use the new model.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# August 15, 2024 | Deepgram's Docs

[August 15, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/8/15)

New Deepgram Models Endpoint
----------------------------

The Deepgram Models endpoint allows users to efficiently query all available public models or private models and determine which models they have access to. You can also use this endpoint to retrieve important model metadata for all Deepgram Models.

*   To learn more about this feature see our [Documentation on Model Metadata.](https://developers.deepgram.com/docs/model-metadata)
    

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# Speech-to-Text | Deepgram's Docs

[October 16, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/10/16)

Flux: Expanded Audio Format Support
-----------------------------------

Flux now supports a wider range of audio formats beyond `linear16`, giving you more flexibility in how you send audio to our conversational speech recognition model. This update adds support for additional raw audio encodings and containerized audio formats.

### Raw Audio Format Support

Flux now accepts the following raw (non-containerized) audio encodings:

*   `linear16` - 16-bit signed little-endian PCM (existing)
*   `linear32` - 32-bit signed little-endian PCM (new)
*   `mulaw` - Mu-law encoding (new)
*   `alaw` - A-law encoding (new)
*   `opus` - Opus codec (new)
*   `ogg-opus` - Opus in Ogg container (new)

When using raw audio formats, you must specify both the `encoding` and `sample_rate` parameters in your API request.

### Containerized Audio Support

Flux now also accepts containerized audio formats, eliminating the need to manually specify encoding and sample rate parameters:

*   **WAV containers** with `linear16` encoding
*   **Ogg containers** with `opus` encoding

When sending containerized audio, **omit** the `encoding` and `sample_rate` parameters—Flux will automatically detect these from the container metadata.

### Supported Sample Rates

For raw audio, Flux supports the following sample rates:

*   8000 Hz
*   16000 Hz (recommended)
*   24000 Hz
*   44100 Hz
*   48000 Hz

### Implementation

**For raw audio:**

`   wss://api.deepgram.com/v2/listen?model=flux-general-en&encoding=linear16&sample_rate=16000   `

**For containerized audio:**

`   wss://api.deepgram.com/v2/listen?model=flux-general-en   `

For detailed information about Flux audio requirements, see our [Flux documentation](https://developers.deepgram.com/docs/flux/quickstart)
.

* * *

[October 2, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/10/2)

Introducing Flux: Conversational Speech Recognition to Solve the Biggest Problem in Voice Agents – Interruptions
----------------------------------------------------------------------------------------------------------------

#### Flux is here: the first real-time Conversational Speech Recognition model built for voice agents. Solve interruptions, cut latency, and ship natural conversations faster than ever.

Deepgram is proud to announce the release of [Flux](https://deepgram.com/learn/introducing-flux-conversational-speech-recognition)
, the first speech recognition model that knows when someone is actually done talking. Built for conversation, not transcription.

**Key Features:**

*   **Model-integrated turn detection** that understands context and conversation flow, not just silence
*   **Ultra-low latency when it matters most** - transcripts that are ready as soon as turns end
*   **Nova-3 level transcription quality** - high-quality speech-to-text (STT) that’s every bit as accurate as the best models, including keyterm prompting
*   **Radically simpler development** - one API replaces complex STT+VAD+endpointing pipelines, and conversation-native events designed to make voice agent development a breeze
*   **Configurability for your use case** - the right amount of complexity, allowing developers to achieve the desired behavior for their agent

**Use Cases:**

Designed for real-time conversational applications: voice agents, AI assistants, IVR systems, and any application requiring natural dialogue flow. For pure transcription (meetings, captions, recordings), continue using Nova-3.

**Getting Started:**

Flux is **free throughout October 2025** for our OktoberFLUX promotion (up to 50 concurrent connections). Use `model=flux-general-en` via the new `/v2/listen` endpoint.

Learn more in our [Announcement Blog](https://deepgram.com/learn/introducing-flux-conversational-speech-recognition)
, [Developer Documentation](https://developers.deepgram.com/docs/flux/quickstart)
, [API Reference](https://developers.deepgram.com/reference/speech-to-text/listen-flux)
, and try the [Interactive Demo](https://flux.deepgram.com/)
.

### Availability

Flux English is now available through our API. To access:

*   Connect to `wss://api.deepgram.com/v2/listen` using `model=flux-general-en` (reference additional [required params here](https://developers.deepgram.com/reference/speech-to-text/listen-flux)
    
*   Available for hosted use
*   Real-time streaming only
*   Self-hosted support coming soon
*   English-only for now

* * *

[September 16, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/9/16)

Nova-3 Model Update
-------------------

#### 🎯 Nova-3 supports 4 new languages

We’ve added support for 4 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 language support beyond English. The newly supported languages and their corresponding language codes are:

**Newly Supported:**

*   Italian (`it`)
*   Turkish (`tr`)
*   Norwegian (`no`)
*   Indonesian (`id`)

Learn more about Nova-3 on the [Models and Language Overview](https://developers.deepgram.com/docs/models-languages-overview)
 page.

* * *

[September 2, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/9/2)

Nova-3 Model Update
-------------------

#### 🎯 Nova-3 supports 3 new languages

We’ve added support for 3 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 language support beyond English. The newly supported languages and their corresponding language codes are:

**Newly Supported:**

*   Spanish (`es`, `es-419`)
*   French (`fr`, `fr-CA`)
*   Portuguese (`pt`, `pt-BR`, `pt-PT`)

Learn more about Nova-3 on the [Models and Language Overview](https://developers.deepgram.com/docs/models-languages-overview)
 page.

* * *

[August 15, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/8/15)

Nova-3 Model Update
-------------------

#### 🎯 Nova-3 supports 4 new languages

We’ve added support for 4 new languages with non-English monolingual Nova-3 models. This is the beginning of an effort to significantly expand Nova-3 language support beyond English. The newly supported languages and their corresponding language codes are:

**Newly Supported:**

*   German (`de`)
*   Dutch (`nl`)
*   Swedish (`sv`, `sv-SE`)
*   Danish (`da`, `da-DK`)

Learn more about Nova-3 at [Models and Language Overview](https://developers.deepgram.com/docs/models-languages-overview)
 page

* * *

[June 11, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/6/11)

Profanity Filtering Expanded Language Support
---------------------------------------------

### Profanity Filtering Gets Expanded Language Support

Profanity filtering now supports **6 additional languages** beyond English, giving you content moderation capabilities across your global user base. Available on monolingual models for:

**Newly Supported:**

*   German (`de`)
*   Swiss German (`de-CH`)
*   Polish (`pl`)
*   Portuguese (`pt`, `pt-BR`, `pt-PT`)
*   Spanish (`es`, `es-419`)
*   Swedish (`sv`, `sv-SE`)

**Existing English Support:**

*   `en`, `en-US`, `en-AU`, `en-GB`, `en-NZ`, `en-IN`

This expansion lets you deploy consistent content policies across international markets without building custom filtering logic.

### Smart Formatting Improvements

We’ve resolved several high-impact formatting edge cases that were causing transcription accuracy issues in production environments:

### Improved Entity Formatting via Smart Format

**Email Transcription Improvements**

*   **Fixed:** `'o'` characters in email addresses now transcribe correctly instead of converting to `'0'`
*   **Fixed:** edge case email mentions that were being dropped entirely in specific batch processing scenarios

**Certain formerly numeric-only sequences have been updated to correctly preserve all alphanumeric characters:**

*   Before (some entities): `"my account number is a b c d zero nine"` → `"my account number is 09"`
*   After (some entities): `"my account number is a b c d zero nine"` → `"my account number is ABCD09"`

**Quantity modifiers (‘single’, ‘double’, ‘triple’ + standalone character or number) are better handled via Smart Format:**

*   Before (some entities): `"double 2"` → `"2"`
*   After (some entities): `"double 2"` → `"22"`

**Special cases of ‘hundred’ or ‘a hundred’ now supported via Smart Format:**

*   Before (some entities): `"hundred percent"` → `"%"`
*   After (some entities): `"hundred percent"` → `"100%"`

This update has gone out to all hosted streaming transcription, and will be applied to our next self-hosted release later this month.

* * *

[May 21, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/5/21)

Nova-3 Medical Streaming Significant Upgrade
--------------------------------------------

We’ve just released a significant upgrade to **Nova-3 Medical Streaming**, bringing substantial improvements in accuracy for real-time medical transcription use cases. This update focuses specifically on our **streaming model**, delivering better performance across key transcription metrics.

### Performance Improvements

*   \*\*11% relative reduction in Overall WER \*\*compared to Nova-3 general streaming model
*   \*\*30% relative reduction in Overall WER \*\*compared to Nova-2 Medical streaming model
*   \*\*2.7x improvement in Keyword Recall Rate (KRR) \*\*compared to Nova-3 general streaming model
*   Maintains industry-leading inference speed with ultra-low latency for real-time healthcare applications

### Availability

The updated Nova-3 Medical streaming model is now available through our API. To access:

*   Use `model=nova-3-medical` in your streaming API calls
*   Available for hosted use
*   Self-hosted deployments will be available in subsequent releases
*   English only

For details on the original Nova-3 Medical release (including batch capabilities), check out the original changelog: [Introducing Nova-3 Medical.](https://deepgram.com/changelog/introducing-nova-3-medical)
 For detailed information about Nova-3 Medical, please refer to our [Developer Documentation](https://developers.deepgram.com/docs/models-languages-overview#nova-3)
.

* * *

[April 2, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/4/2)

Smart Formatting Improvements
-----------------------------

We’ve made some improvements to Smart Formatting, enhancing both streaming finalization behavior and entity recognition performance.

### Streaming Finalization Improvements

Previously, when formatting entities like dates or credit card numbers, our models would sometimes wait for additional words before finalizing the transcript—particularly if the entity seemed incomplete. For example, when someone said “nineteen seventy…” Deepgram might pause, expecting a possible follow-up like “nine” or other additional speech before finalizing the complete year.

Now, instead of potentially waiting indefinitely for additional words, our system will finalize the transcript after **3 seconds of silence**, and attempt to format the entity based on the available audio. This helps ensure transcripts are returned faster and more reliably—without sacrificing too much formatting precision.

Want more control over the finalization behavior? You have two options:

*   Implement logic to send a `Finalize` message earlier than the 3-second threshold. Reference our [Finalize documentation](https://developers.deepgram.com/docs/finalize)
     here.
*   Set `no_delay=true` to override formatting and force immediate finalization. NOTE: This will result in skipping formatting altogether in many cases.

### Enhanced Entity Formatting

In addition to the timeout improvements, we’ve refined our [Named Entity Recognition](https://deepgram.com/ai-glossary/named-entity-recognition)
 model for Smart Formatting to better identify and format:

*   Date variations
*   Alphanumerics (order numbers, membership IDs, prescription numbers, etc.)
*   Currencies
*   Payment and card information
*   SSNs
*   Time zones

This update is automatically applied to all streaming transcription using Smart Formatting, and is included in our Self-Hosted March 2025 Release (250331). For more details, check out our [Smart Formatting documentation](https://developers.deepgram.com/docs/smart-format)
.

* * *

[March 31, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/3/31)

Nova-3 Multilingual General Availability - Real-Time Code-Switching
-------------------------------------------------------------------

Deepgram is proud to announce the general availability of Nova-3 Multilingual, the first model of its kind able to codeswitch in real-time across 10 different languages. This revolutionary capability unlocks a host of new possibilities for global operations by processing multilingual conversations instantly with a single model—an industry-first breakthrough that changes the game for speech recognition.

### Multilingual Support

*   **Real-time multilingual speech recognition** with a truly unified speech recognition system
    
*   Supports code-switching between 10 languages:
    
    *   English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch
*   Seamlessly handles natural language transitions without relying on explicit routing or language-specific mechanisms
    
*   Maintains high transcription accuracy across languages while adapting to natural language transitions
    
*   Developed through a multi-stage training process combining synthetic code-switched data at massive scale with carefully curated real-world datasets
    

### Use Cases

Nova-3 Multilingual represents a significant breakthrough for applications in:

*   Global customer support
*   Emergency response (e.g., 911 calls)
*   Multilingual meetings
*   Retail interactions
*   Healthcare settings

In high-stakes scenarios like emergency response, Nova-3 can fluidly process interactions where callers switch between languages (e.g., Spanish and English) in real time, ensuring dispatchers receive accurate, immediate transcriptions without missing critical details.

### Availability

*   Now available through our API
*   Use `model=nova-3&language=multi` in your API calls
*   Supports both pre-recorded and real-time streaming transcription
*   Available for hosted and self-hosted use

For detailed information about Nova-3 Multilingual, please refer to our [Developer Documentation](https://developers.deepgram.com/docs/multilingual-code-switching)
.

* * *

[March 11, 2025](https://developers.deepgram.com/changelog/speech-to-text-changelog/2025/3/11)

Expanded Numerals Language Support
----------------------------------

Deepgram is excited to announce expanded language support for numerals through our `numerals` and `smart_format` parameters, providing more comprehensive coverage for converting written numbers to numerical format across additional languages.

### Expanded Language Support

*   **New languages added to Numerals support:**
    *   Danish: `da`, `da-DK`
    *   Dutch: `nl`
    *   French: `fr`, `fr-CA`
    *   German: `de`
    *   German (Switzerland): `de-CH`
    *   Italian: `it`
    *   Norwegian: `no`
    *   Polish: `pl`
    *   Portuguese: `pt`, `pt-BR`, `pt-PT`
    *   Spanish: `es`, `es-419`
    *   Swedish: `sv`, `sv-SE`

**Previously supported language:**

*   English: `en`, `en-US`, `en-AU`, `en-GB`, `en-NZ`, `en-IN`

### Feature Integration

*   All newly supported languages are fully integrated with our Smart Format feature
*   When using `smart_format=true`, numerals will automatically be applied for all supported languages
*   Individual control remains available through the dedicated `numerals=true` parameter

### Availability

The expanded Numerals support is now available through our API for use with all Deepgram speech-to-text models.

*   Available for hosted and self-hosted usage.
*   Compatible with both pre-recorded and real-time streaming transcription

For detailed information about our expanded [Numerals](https://deepgram-preview-e9e61f4a-067d-48e1-9981-892b671eaaf8.docs.buildwithfern.com/docs/numerals)
 or [Smart Formatting](https://deepgram-preview-e9e61f4a-067d-48e1-9981-892b671eaaf8.docs.buildwithfern.com/docs/smart-format)
 support, please refer to our Developer Documentation.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# July 22, 2024 | Deepgram's Docs

[July 22, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/7/22)

Entity Detection Feature General Availability
---------------------------------------------

We’re thrilled to announce the GA release of our entity detection feature for Deepgram Hosted customers.

`detect_entities=true`

By including the new parameter in your pre-recorded speech-to-text requests (STT), you can identify and extract over 50 unique entity types. This release brings up to a 74% absolute improvement in detecting email addresses, names, locations, phone numbers, social security numbers, and more.

*   See our [Entity Detection documentation](https://developers.deepgram.com/docs/detect-entities)
     and \[supported entity types\]([https://developers.deepgram.com/docs/supported-entity-types](https://developers.deepgram.com/docs/supported-entity-types)
     for information.) to learn more about using Entity Detection.
*   For Self-Hosted customers, please reach out to your Deepgram contact if you’d like to use the new feature in beta.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# September 28, 2023 | Deepgram's Docs

[September 28, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/9/28)

Enhanced Redaction Options for Pre-Recorded Audio
-------------------------------------------------

Deepgram’s latest update offers enhanced redaction options for customers submitting pre-recorded audio to our hosted endpoint.

Customers can now select specific types of entities, like locations, URLs, or names, to be redacted from their transcriptions.

Here’s an example of how to accomplish redacting different types of entities (in this case, city names, ages, and emails):

For more information, head over to our [developer documentation](https://developers.deepgram.com/docs/redaction)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# June 2, 2023 | Deepgram's Docs

[June 2, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/6/2)

New KeepAlive Feature for Streaming Connections
-----------------------------------------------

Customers can now keep Deepgram streaming connections open during periods where no audio data is being sent. Previously, if no audio was being sent over the websocket, connections would close after a short window of time. We’ve introduced a new KeepAlive WebSocket message that clients can use to indicate to Deepgram that the WebSocket should be kept open even though no data is being sent through.

For more information, visit our [documentation](https://developers.deepgram.com/reference/streaming#stream-keepalive)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# May 24, 2024 | Deepgram's Docs

[May 24, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/5/24)

Nova-2 Medical Accuracy Improvements
------------------------------------

`model = nova-2-medical`

Deepgram has done additional training to our Nova-2 Medical Model to improve accuracy and expand the model vocabulary - resulting in a 16% relative improvement in word recall rate (WRR) on key medical terminology.

See our docs for the full list of models available: [https://developers.deepgram.com/docs/models-languages-overview](https://developers.deepgram.com/docs/models-languages-overview#nova-2)

There should be no code changes required on your end - all requests with model=nova-2-medical will automatically get the latest version with the fix applied.

For On-Premises customers, please reach out to your Deepgram contact if you’d like to update your models.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# May 11, 2023 | Deepgram's Docs

[May 11, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/5/11)

Enhanced Automatic Language Detection
-------------------------------------

We are thrilled to release the enhanced version of our Automatic Language Detection feature (detect\_language=true), now supporting over 15+ languages. Deepgram’s Enhanced Language Detection is adept at identifying the primary language in an audio file and providing transcriptions in the detected language.

To utilize the Language Detection API, simply use the following URL query format: 

`https://api.deepgram.com/v1/listen?detect_language=true&punctuate=true`

The API Response will output the detected language. For example – _“detected\_language”: “es”_

To learn more about the various parameters you can use to customize your transcriptions with Deepgram, check out the list of Deepgram’s [features in our documentation](https://developers.deepgram.com/docs/features-overview)
.  

If you have any questions, please reach out to us through your dedicated support channel.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# July 16, 2024 | Deepgram's Docs

[July 16, 2024](https://developers.deepgram.com/changelog/speech-to-text-changelog/2024/7/16)

Nova-2 Multilingual Code-Switching Support
------------------------------------------

`model=nova-2&language=multi`

We’re excited to announce that we have released our\*\* multilingual code-switching support (Spanish and English)\*\* in our next-gen speech-to-text model, Nova-2.

With full pre-recorded and streaming capabilities, and word-level language classification, it’s optimized for all your complex code-switching use cases in an increasingly multilingual world.

See our [multilingual code-switching documentation](https://developers.deepgram.com/docs/multilingual-code-switching)
 for information.

For Self-Hosted customers, please reach out to your Deepgram contact if you’d like to use the new feature.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# June 30, 2023 | Deepgram's Docs

[June 30, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/6/30)

Introducing Nova - Most Powerful Speech-to-Text Model
-----------------------------------------------------

Nova is Deepgram’s most powerful and affordable speech-to-text model. Training on this model spans over 100 domains and 47 billion tokens, making it the deepest-trained automatic speech recognition (ASR) model to date. Nova doesn’t just excel in one specific domain — it is ideal for a wide array of voice applications that require high accuracy in diverse contexts.

This model now support the Spanish language es and es-419.

*   Learn more about using our new [Nova Model.](https://developers.deepgram.com/docs/nova-quickstart)
    
*   Quickly test out this new Model using our [API Playground.](https://playground.deepgram.com/)
    
*   Learn more about [Deepgram Language Support.](https://developers.deepgram.com/docs/language)
    

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# October 17, 2022 | Deepgram's Docs

[October 17, 2022](https://developers.deepgram.com/changelog/speech-to-text-changelog/2022/10/17)

Real-Time API Enhanced Usability Update
---------------------------------------

Deepgram’s real-time API has been updated for enhanced usability.

Streaming connections should now be closed by sending the JSON message `{ "type": "CloseStream" }` . Previously, streaming connections were closed by sending an empty byte.

Here’s an example of sending a CloseStream message in Javascript:

And an example in Python:

In the future, we will deprecate the ability to close the connection with an empty byte.  We recommend customers using our API move to using the CloseStream method to avoid potential disruptions. Any customers using our SDK will not need to make changes.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# March 15, 2023 | Deepgram's Docs

[March 15, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/3/15)

New Endpointing Feature with Voice Activity Detection
-----------------------------------------------------

Deepgram is excited to announce a new version of the Endpointing feature. Endpointing is designed to get customers the fastest and most accurate transcripts. It can also help determine when someone has finished talking. Users can specify the amount of silence they want to wait for when someone finishes talking before Deepgram finalizes the transcript and returns it with the flag `speech_final`.

The Endpointing feature utilizes a powerful Voice Activity Detection algorithm to determine when someone has stopped speaking. Once speech has finished, Deepgram is able to quickly finalize a transcription of the speech and return it, along with a `speech_final` flag marking that an Endpoint was detected.

This algorithm can be configured through our Endpointing feature. To find out more, head to our [Endpointing documentation](https://developers.deepgram.com/docs/endpointing)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# February 27, 2023 | Deepgram's Docs

[February 27, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/2/27)

English General Model Base and Enhanced Tier Improvements
---------------------------------------------------------

New versions of our English (en-US) General model’s Base and Enhanced tiers have greatly improved accuracy and throughput. We are incredibly excited to release these enhancements to our customers. We are making the new tiers available for testing over the next two weeks so you can compare them to your current results. If you are interested in testing the new tiers please reach out to Deepgram support to enable access. We will be deploying the new tiers as defaults on March 14th, 2023.

If you do not wish to use the new versions that will be deployed as the default on March 14, 2023, you may pin to previous versions by specifying the desired version as version={desired\_version}. If no version is specified, we will use our latest version by default. 

Most recent previous versions of these tiers:

Base (model=general)

2022-01-18.1

Enhanced (model=general)

2022-05-18.0

Deepgram support is always available to walk customers through updates, as well as resolve any issues that arise when upgrading.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# October 14, 2022 | Deepgram's Docs

[October 14, 2022](https://developers.deepgram.com/changelog/speech-to-text-changelog/2022/10/14)

Enhanced Model Support Expanded to German Language
--------------------------------------------------

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include German to bring you the highest accuracy for German language support.

For example, to call the Enhanced German Model, the URL query might look like

_[https://api.deepgram.com/v1/listen?model=general&tier=enhanced&language=de&punctuate=true](https://api.deepgram.com/v1/listen?model=general&tier=enhanced&language=de&punctuate=true)
_

To learn more about the various parameters you can use to customize your transcriptions with Deepgram, check out the list of Deepgram’s [features in our documentation](https://developers.deepgram.com/documentation/features/)
. 

Before using the new Model in production, we recommend testing it alongside your typical feature adds, like keywords. Model updates may change transcription outputs.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---

# April 13, 2023 | Deepgram's Docs

[April 13, 2023](https://developers.deepgram.com/changelog/speech-to-text-changelog/2023/4/13)

Latest Speech Recognition Model Releases
----------------------------------------

We are pleased to announce the latest model releases to our speech recognition services.

### Deepgram Nova

Deepgram Nova presents the new state-of-the-art in speech recognition. Read more about it in [our announcement](https://blog.deepgram.com/nova-speech-to-text-whisper-api/)
.

Nova is available with our `general` and `phonecall` models. To access either, please use the following syntax in your request:

*   General: `model=nova` or `model=general&tier=nova`
*   Phonecall: `model=phonecall&tier=nova`

Support for Deepgram Nova includes:

*   English language support.
*   Pre-recorded and live streaming audio transcription.
*   Use through Deepgram’s Hosted API or [On-Prem](https://deepgram.com/changelog/deepgram-on-premises-april-release-230413/)
     Deployments.

Please view pricing at [deepgram.com/pricing](https://deepgram.com/pricing)
.

### Deepgram Whisper Cloud and Whisper On-Prem

Deepgram Whisper Cloud and Whisper On-Prem integrate [OpenAI’s Whisper models](https://github.com/openai/whisper)
 with Deepgram’s powerful API and feature set.

Deepgram Whisper Cloud and Whisper On-Prem can be accessed with the following API parameters:

*   `model=whisper` or `model=whisper-SIZE`
    
*   Available sizes include:
    
    *   `whisper-tiny`
    *   `whisper-base`
    *   `whisper-small`
    *   `whisper-medium` (default)
    *   `whisper-large` (defaults to OpenAI’s `large-v2`)
*   \*Note: You should not specify a \*`tier` _when using Whisper models._
    

Use of Deepgram Whisper Cloud is subject to a rate limit of 50 requests per minute or 15 concurrent requests.

Support for Deepgram Whisper Cloud and Whisper On-Prem include:

*   A selection of Deepgram’s transcription features, including:
    
    *   Diarization
        
    *   Word-level time stamps
        
    *   Language detection
        
    *   Redaction
        
    *   Diarization
        
    *   Smart Formatting
        
        *   Punctuation, Numeral Formatting, Find and Replace, Paragraphs, Utterances
    *   Multichannel Support
        
    *   Callback Support
        
    *   Summarization
        
    *   Topic Detection
        
*   OpenAI’s [list of supported languages](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py)
    .
    
*   Pre-recorded transcription.
    
*   Use through Deepgram’s Hosted API or [On-Prem](https://deepgram.com/changelog/deepgram-on-premises-april-release-230413/)
     [Deployments](https://developers.deepgram.com/on-prem/required/)
    .
    

Please view pricing at [deepgram.com/pricing](https://deepgram.com/pricing)
.

To learn more about the various parameters you can use to customize your transcriptions with Deepgram, check out the list of Deepgram’s [**features in our documentation**](https://developers.deepgram.com/documentation/features/)
.

[![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-light.svg)![Logo](https://files.buildwithfern.com/https://deepgram.docs.buildwithfern.com/2025-10-22T20:35:17.279Z/assets/logo-dark.svg)](https://developers.deepgram.com/)

[Playground](https://playground.deepgram.com/)
[Console](https://console.deepgram.com/)
[Community](https://community.deepgram.com/)
[Support](https://developers.deepgram.com/docs/support)
[Free API Key](https://console.deepgram.com/signup)

---