Data and AI releases

548 this month · 176 companies

defer_until_eot

UpdateNot yet verified

Add defer_until_eot: true to any function in agent.think.functions to hold it until the turn is confirmed. If the user keeps speaking and the turn resumes, the call is discarded before it does anything.

AI agents

Also shipped Sep 8, 2026Deepgram in September 2026 →

Shadow traffic for gateways (Preview)

With this preview release, you can use a shadow traffic gateway to send all production requests to a primary service endpoint while mirroring a percentage of those requests to one or more shadow endpoints. Responses from shadow endpoints aren't returned to clients.

Preview
Source ↗

ABAC DENY policies are in Beta

ABAC DENY policies are in Beta in Unity Catalog. DENY policies can be used to explicitly deny the MANAGE ACCESS CONTROL privilege to prevent specified principals, including object owners, from performing access-management operations. They always take precedence over any grant. For details, see ABAC DENY policies (Beta) .

Beta
Source ↗

More from DeepgramEvery Deepgram release →

FunctionCallCancelled

Clients now receive an explicit signal when a client-side function call they were sent is cancelled because the user started speaking again, either inside the speculative window (the turn resumed) or after the turn was confirmed (barge-in). Only calls the client already received are announced.

Update
Source ↗

@deepgram/react 0.2.0

@deepgram/react 0.2.0 adds runtime Voice Agent controls and makes React session lifecycle handling safer. The release updates the React layer for @deepgram/agents 0.1.2 and @deepgram/sdk 5.9.0.

Update
Source ↗

Runtime controls and notifications

Use sendAgentMessage() to inject an agent message with "default" , "queue" , or "interrupt" behavior. Use updateListen() , updateThink() , updateSpeak() , and updatePrompt() to change supported agent settings during a session.

Update
Source ↗

Lifecycle and upgrade notes

Start, stop, reconnect, and React StrictMode handling now clean up canceled or failed microphone, playback, and client-tool resources. Automatic start failures call onSdkError , or console.error when no callback is set. A manual start() call rejects instead. This is a 0.2.0 release.

Update
Source ↗

New language

- Kazakh ( kk , kk-KZ ) , available for batch and streaming. Access this language by setting model="nova-3" and language="kk" in your request.

Update
Source ↗

Improved models

Batch and streaming models Polish ( pl ) Hebrew ( he ) Batch models Macedonian ( mk ) Streaming models Estonian ( et ) Latvian ( lv ) Lithuanian ( lt ) Malay ( ms ) You do not need to change your API requests to access the improvements to existing languages; the updates are live for all users.

Update
Source ↗