Data and AI releases

548 this month · 176 companies

Numerals Support Now Available for 3 New Languages: Russian, Romanian, and Hebrew (Monolingual Models)

UpdateNot yet verified

Supported languages and language codes: Russian ( ru ) Romanian ( ro ) Hebrew ( he ) You can now use Deepgram’s Numerals feature with monolingual models for Russian, Romanian, and Hebrew. Numerals converts spoken numbers into digits (for example, "three hundred" → "300") in your transcript, helping you create more accurate and easily processed results.

Developer tools

Also shipped May 15, 2026Deepgram in May 2026 →

What's new in Sigma

API Custom SQL elements included in the response for List sources endpoints The List data model sources ( GET /v2/data-models/{dataModelId}/sources ), List workbook sources ( GET /v2/workbooks/{workbookId}/sources ), and List report sources ( GET /v2/reports/{reportId}/sources ) endpoints now include custom SQL elements in the response.

GA
Source ↗

Railway for iOS, CLI metrics, Postgres PITR

This week, the Railway iOS app [landed in TestFlight](https://railway.com/mobile)! You can spin up services, get notified if anything goes wrong, read logs, view metrics, and deploy fixes, all from your pocket. No more keeping a laptop within arm's reach every weekend.

Preview
Source ↗

More from DeepgramEvery Deepgram release →

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 detects and redacts offensive language in transcripts, helping you produce cleaner and safer content across a wide range of languages.

Update
Source ↗

How to Use Profanity Filtering

To enable profanity filtering, add the profanity_filter=true parameter to your Deepgram API request: For more details, supported languages, and additional options, visit the Profanity Filter page .

Update
Source ↗

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 model. v2 is a new architecture available today on an opt-in basis through the new diarize_model parameter.

GA
Source ↗

Nova-3 Portuguese Model Update

Improved Nova-3 Portuguese Model We’ve enhanced the Nova-3 Portuguese model with improved transcription accuracy across Portuguese language variants, including Brazilian Portuguese ( pt-BR ) and European Portuguese ( pt-PT ).

Update
Source ↗

Nova-3 Multilingual Model Update

Numerals Support Expanded for Nova-3 Multilingual Numeral formatting is now supported for all Nova-3 multilingual languages , except Hindi and Japanese. This enhancement means Nova-3 multilingual can now convert spoken numbers to digits (e.g., "three hundred" → "300") for English, Spanish, French, German, Russian, Portuguese, Italian, and Dutch.

Update
Source ↗

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 agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.1-flash-lite", "temperature": 0.5 } } } }

Preview
Source ↗

Deprecations

- gemini-3.1-flash-lite-preview is deprecated and will be removed on May 26, 2025. Migrate to gemini-3.1-flash-lite . For more details on Gemini model deprecations, see Google's Gemini deprecations page . For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .

Deprecation
Source ↗

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, floating, inline, button, embedded, or orb). No framework required.

Update
Source ↗