Deepgram

AI

A speech-to-text, text-to-speech and voice-agent API.

Latest · by DeepgramWebsite

Release activity

Release activity — 29 releases across 29 days since Nov 7, 2025. Each cell is one day; darker means more releases that day. Nothing is recorded before Nov 7, 2025. Older weeks are hidden at this screen width.
MayJunJulAug
SundayNo releases on Apr 26, 2026No releases on May 3, 2026No releases on May 10, 2026No releases on May 17, 2026No releases on May 24, 2026No releases on May 31, 2026No releases on Jun 7, 2026No releases on Jun 14, 2026No releases on Jun 21, 2026No releases on Jun 28, 2026No releases on Jul 5, 2026No releases on Jul 12, 2026No releases on Jul 19, 2026No releases on Jul 26, 2026No releases on Aug 2, 2026No releases on Aug 9, 2026
MondayNo releases on Apr 27, 20261 release on May 4, 20261 release on May 11, 2026No releases on May 18, 2026No releases on May 25, 2026No releases on Jun 1, 2026No releases on Jun 8, 20261 release on Jun 15, 2026No releases on Jun 22, 2026No releases on Jun 29, 2026No releases on Jul 6, 2026No releases on Jul 13, 2026No releases on Jul 20, 2026No releases on Jul 27, 2026No releases on Aug 3, 20261 release on Aug 10, 2026
TuesdayNo releases on Apr 28, 2026No releases on May 5, 20261 release on May 12, 20261 release on May 19, 2026No releases on May 26, 2026No releases on Jun 2, 2026No releases on Jun 9, 2026No releases on Jun 16, 2026No releases on Jun 23, 2026No releases on Jun 30, 2026No releases on Jul 7, 2026No releases on Jul 14, 2026No releases on Jul 21, 2026No releases on Jul 28, 2026No releases on Aug 4, 2026No releases on Aug 11, 2026
Wednesday1 release on Apr 29, 2026No releases on May 6, 20261 release on May 13, 2026No releases on May 20, 20261 release on May 27, 2026No releases on Jun 3, 2026No releases on Jun 10, 2026No releases on Jun 17, 2026No releases on Jun 24, 20261 release on Jul 1, 2026No releases on Jul 8, 2026No releases on Jul 15, 2026No releases on Jul 22, 2026No releases on Jul 29, 20261 release on Aug 5, 2026
ThursdayNo releases on Apr 30, 2026No releases on May 7, 20261 release on May 14, 20261 release on May 21, 2026No releases on May 28, 2026No releases on Jun 4, 2026No releases on Jun 11, 2026No releases on Jun 18, 2026No releases on Jun 25, 20261 release on Jul 2, 2026No releases on Jul 9, 2026No releases on Jul 16, 2026No releases on Jul 23, 2026No releases on Jul 30, 2026No releases on Aug 6, 2026
FridayNo releases on May 1, 2026No releases on May 8, 20261 release on May 15, 2026No releases on May 22, 20261 release on May 29, 2026No releases on Jun 5, 2026No releases on Jun 12, 2026No releases on Jun 19, 2026No releases on Jun 26, 2026No releases on Jul 3, 2026No releases on Jul 10, 2026No releases on Jul 17, 2026No releases on Jul 24, 2026No releases on Jul 31, 20261 release on Aug 7, 2026
SaturdayNo releases on May 2, 2026No releases on May 9, 2026No releases on May 16, 2026No releases on May 23, 2026No releases on May 30, 2026No releases on Jun 6, 2026No releases on Jun 13, 2026No releases on Jun 20, 2026No releases on Jun 27, 2026No releases on Jul 4, 2026No releases on Jul 11, 2026No releases on Jul 18, 2026No releases on Jul 25, 2026No releases on Aug 1, 2026No releases on Aug 8, 2026

29 releases since Nov 7, 2025

Changelog

August 10, 2026

Nova-3 Adds Armenian, Plus Improved Models for Tamil, Indonesian, and Belarusian We have added Armenian as a new Nova-3 language and released improved Nova-3 monolingual models for several existing la…

Added 1
  • Added Armenian as a new Nova-3 language
Changed 1
  • Released improved Nova-3 monolingual models for Tamil, Indonesian, and Belarusian
View originalPermalink
How August 10, 2026 went

August 7, 2026

Improved Models Released for Multiple Languages We have released improved Nova-3 monolingual models for the following languages. These updates enhance transcription quality and accuracy for both batch…

Changed 1
  • Released improved Nova-3 monolingual models for multiple languages with enhanced transcription quality and accuracy for batch processing
View originalPermalink
How August 7, 2026 went

August 5, 2026

Nova-3 Model Update 🌏 Nova-3 monolingual models now support Punjabi and Nepali with the following language codes: Punjabi: pa , pa-IN Nepali: ne Batch and streaming models are both available for thes…

Added 3
  • Nova-3 monolingual models now support Punjabi with language codes pa and pa-IN
  • Nova-3 monolingual models now support Nepali with language code ne
  • Batch and streaming models are both available for Punjabi and Nepali
View originalPermalink
How August 5, 2026 went

July 2, 2026

Flux Word-Level Timestamps 🆕 Word-Level Timestamps Now Available in Flux Flux now includes word-level timestamps in its responses. Each word in the words array carries start and end times (type doubl…

Added 1
  • Word-level timestamps now available in Flux with start and end times for each word in the words array
View originalPermalink
How July 2, 2026 went

July 1, 2026

Claude Sonnet 5 Now Available claude-sonnet-5 is now available as a managed Anthropic LLM in the Voice Agent API. This Advanced tier model delivers improved reasoning and conversational quality for yo…

Added 1
  • Claude Sonnet 5 is now available as a managed Anthropic LLM in the Voice Agent API for Advanced tier users
View originalPermalink
How July 1, 2026 went

June 15, 2026

UpdateListen: On-the-Fly Listen Configuration You can now update the Listen configuration during a conversation without restarting the session. Send an UpdateListen message to tune: eot_threshold — en…

Added 1
  • UpdateListen message to modify Listen configuration on-the-fly during a conversation without restarting the session, including tuning eot_threshold
View originalPermalink
How June 15, 2026 went

May 29, 2026

Nova-3 Medical Batch Model Upgrade 🆕 Improved Nova-3 Medical Batch Model Released We’ve released an upgraded Nova-3 Medical batch model with improved medical term recognition. Key Improvements: Expan…

Added 1
  • Released upgraded Nova-3 Medical batch model with improved medical term recognition
View originalPermalink
How May 29, 2026 went

May 27, 2026

Gemini 3.5 Flash Now Available gemini-3.5-flash is now available as a managed Google LLM in the Voice Agent API. This Standard tier model brings improved performance and efficiency to your voice agent…

Added 1
  • gemini-3.5-flash is now available as a managed Google LLM in the Voice Agent API
View originalPermalink
How May 27, 2026 went

May 21, 2026

Profanity Filtering Now Supported for All Multilingual Models; Korean Spacing Improvements 🆕 Profanity Filtering for Multilingual Models Deepgram’s Profanity Filtering feature is now available for al…

Added 1
  • Profanity Filtering feature is now available for all multilingual models
Changed 1
  • Korean spacing improvements
View originalPermalink
How May 21, 2026 went

May 19, 2026

Gemini 3.1 Flash Lite Now Available gemini-3.1-flash-lite is now available as a managed Google LLM in the Voice Agent API. This Standard tier model replaces the preview version. Set the model in your…

Added 1
  • Gemini 3.1 Flash Lite is now available as a managed Google LLM in the Voice Agent API as a Standard tier model
View originalPermalink
How May 19, 2026 went

May 15, 2026

Numerals Support Now Available for 3 New Languages: Russian, Romanian, and Hebrew (Monolingual Models) Supported languages and language codes: Russian ( ru ) Romanian ( ro ) Hebrew ( he ) You can now…

Added 1
  • Support for numerals in Russian, Romanian, and Hebrew monolingual models
View originalPermalink
How May 15, 2026 went

May 14, 2026

Profanity Filtering Now Available in 50+ Languages We're excited to announce the release of profanity filtering support for over 50 monolingual languages. Deepgram's profanity filter automatically det…

Added 1
  • Profanity filtering support for over 50 monolingual languages
View originalPermalink
How May 14, 2026 went

May 13, 2026

Diarization v2: Improved Batch Speaker Diarization A new batch diarization model is available today via the diarize_model API parameter. Deepgram is rolling out v2 of our batch speaker diarization mod…

Added 1
  • New batch diarization model available via the diarize_model API parameter
Changed 1
  • Improved batch speaker diarization with v2 model
View originalPermalink
How May 13, 2026 went

May 12, 2026

SDK releases A new round of SDK updates is now available across JavaScript, Rust, Python, and Java. This release brings Flux multilingual support to Rust, restores the Agent interface in JavaScript, s…

Added 2
  • Add Flux multilingual support to Rust SDK
  • Restore Agent interface in JavaScript SDK
View originalPermalink
How May 12, 2026 went

May 11, 2026

Browser Agent SDK The Browser Agent SDK is now available — four composable packages that connect any web app to the Voice Agent API: @deepgram/agents-widget — drop-in widget with six layouts (sidebar,…

Added 1
  • Browser Agent SDK is now available as four composable packages for connecting web apps to the Voice Agent API
View originalPermalink
How May 11, 2026 went

May 4, 2026

Aura-2 Voice Controls — Speed and Pronunciation Aura-2 TTS voices now support runtime speed and pronunciation controls in English and Spanish, available on both batch and streaming WebSocket endpoints…

Added 1
  • Aura-2 TTS voices now support runtime speed and pronunciation controls in English and Spanish on both batch and streaming WebSocket endpoints
View originalPermalink
How May 4, 2026 went

April 29, 2026

LLM Model Updates & Cartesia Speed Control GPT-5.5 LLM Model Support OpenAI's GPT-5.5 model is now available as a managed LLM in the Voice Agent API. GPT-5.5 is an Advanced tier model. Set the model i…

Added 1
  • OpenAI's GPT-5.5 model is now available as a managed LLM in the Voice Agent API
View originalPermalink
How April 29, 2026 went

April 23, 2026

Nova-3 Model Update 🌏 Nova-3 now supports Gujarati with the following language codes: Gujarati: gu , gu-IN Access this model by setting model="nova-3" and the relevant language code in your request.…

Added 1
  • Nova-3 model now supports Gujarati language with language codes gu and gu-IN
View originalPermalink
How April 23, 2026 went

April 15, 2026

Deepgram CLI Is Now Available The Deepgram CLI brings transcription, speech synthesis, text analysis, account management, and MCP tooling to your terminal through a single dg command. What you can do…

Added 1
  • Deepgram CLI is now available with transcription, speech synthesis, text analysis, account management, and MCP tooling accessible through the dg command
View originalPermalink
How April 15, 2026 went

March 31, 2026

Nova-3 Model Update 🌏 Nova-3 now supports the following new languages and language codes: Chinese (Mandarin, Simplified): zh , zh-CN , zh-Hans Chinese (Mandarin, Traditional): zh-TW , zh-Hant Access…

Added 2
  • Nova-3 model now supports Chinese (Mandarin, Simplified) with language codes zh, zh-CN, zh-Hans
  • Nova-3 model now supports Chinese (Mandarin, Traditional) with language codes zh-TW, zh-Hant
View originalPermalink
How March 31, 2026 went

March 9, 2026

Reasoning mode for OpenAI thinking models You can now control the reasoning effort of supported OpenAI reasoning models using the new reasoning_mode parameter in the think provider configuration. This…

Added 1
  • Add reasoning_mode parameter to think provider configuration for controlling reasoning effort of supported OpenAI reasoning models
View originalPermalink
How March 9, 2026 went

February 6, 2026

🤖 New OpenAI & Gemini LLM Models Support We've added support for new LLM models in our Voice Agent API! Available Models: OpenAI GPT 5.2 Instant (gpt-5.2-instant) OpenAI GPT 5.2 Thinking (gpt-5.2) Go…

Added 2
  • Support for OpenAI GPT 5.2 Instant (gpt-5.2-instant) and OpenAI GPT 5.2 Thinking (gpt-5.2) models in Voice Agent API
  • Support for new Gemini LLM models in Voice Agent API
View originalPermalink
How February 6, 2026 went

February 5, 2026

Nova-3 Multilingual Model Update 🌍 Nova-3 Multilingual Improvements We’ve released an updated Nova-3 multilingual model , delivering accuracy improvements across supported languages , with the larges…

Changed 1
  • Updated Nova-3 multilingual model with accuracy improvements across supported languages
View originalPermalink
How February 5, 2026 went

February 3, 2026

Nova-3 Model Update 🌐 Nova-3 Adds Support for Hebrew, Farsi, and Urdu We're excited to announce the release of new Nova-3 monolingual models for Hebrew , Farsi , and Urdu ! These additions bring indu…

Added 1
  • Nova-3 now supports Hebrew, Farsi, and Urdu languages with new monolingual models
View originalPermalink
How February 3, 2026 went

January 27, 2026

Nova-3 Model Update 🌐 Nova-3 Now Supports Arabic and all major Arabic dialects We're excited to announce the release of the Nova-3 Arabic monolingual model , which now brings industry-leading speech-…

Added 1
  • Nova-3 model now supports Arabic and all major Arabic dialects
View originalPermalink
How January 27, 2026 went

January 16, 2026

Multiple LLM Provider Support We've added new functionality that allows users to specify multiple LLM providers for your Voice Agent, ensuring your agent will automatically fallback to another provide…

Added 1
  • Allow users to specify multiple LLM providers for Voice Agent with automatic fallback to another provider
View originalPermalink
How January 16, 2026 went

January 13, 2026

Flux: WebM Container Support Added Flux now supports the WebM container format with Opus codec, providing seamless compatibility with audio sources that output WebM-formatted audio streams. WebM Conta…

Added 1
  • Flux now supports the WebM container format with Opus codec for audio processing
View originalPermalink
How January 13, 2026 went

November 24, 2025

Nova-3 Model Update 🎯 Nova-3 supports 10 new languages We've added support for 10 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 la…

Added 1
  • Nova-3 supports 10 new languages with non-English monolingual models
View originalPermalink
How November 24, 2025 went

November 7, 2025

Expanded Language Detection: Now Supports 35 Languages for Pre-Recorded Audio Language Detection for pre-recorded (batch) audio now supports 35 languages (previously 16), allowing you to automatically…

Changed 1
  • Language detection for pre-recorded audio now supports 35 languages, expanded from 16
View originalPermalink
How November 7, 2025 went
View all

Discussion