Releasesby GlyphImproved models
Batch and streaming models Bulgarian ( bg ) Batch models Croatian ( hr ) Estonian ( et ) Italian ( it ) Latvian ( lv ) Lithuanian ( lt ) Malay ( ms ) Streaming models Georgian ( ka , ka-GE ) Marathi ( mr ) Telugu ( te ) You do not need to change your API requests to access these improvements; the updates are live for all users.
Also shipped Aug 28, 2026Deepgram in August 2026 →
Monitor and cap external provider costs
Unity Gateway can now track and cap spend on external model providers, such as Amazon Bedrock and Azure AI Foundry, not just Databricks-provided models. If your organization already has capacity commitments directly with a provider, Unity Gateway becomes the single point to track that usage and enforce spend limits across teams and use cases.
Unity Catalog Skills (Beta)
You can now publish, govern, and share agent skills with Unity Catalog. A skill is a first-class Unity Catalog securable ( catalog.schema.skill ) that follows the SKILL.md specification , so you register it once and control who can discover, use, and update it with the same permissions, tags, and audit that protect your tables.
Looker visual modeling canvas for BigQuery enters preview
A drag-and-drop canvas builds and edits LookML models on BigQuery sources: join tables, define dimensions and measures, preview results and publish Explores without writing LookML.
Conversational Analytics verified queries , also known as golden queries , are now generally available
Conversational Analytics verified queries , also known as golden queries , are now generally available. You can also now define verified queries in Looker (Google Cloud core) instances.
Now available in preview, model localization is supported for imported projects
Now available in preview, model localization is supported for imported projects. By default, Looker uses the locale definitions from the importing project only, if the importing project has locale definitions.
More from DeepgramEvery Deepgram release →
Flexible turn-taking control for Flux
Flux now gives you full control over how turns end. Beyond Flux's native end-of-turn detection, you can override it, suppress it entirely, or blend the two , and switch between these modes on the fly, even for a single turn, with a Configure message. Turn-taking goes from a fixed behavior to something you shape around each moment of a conversation.
Three modes of turn-taking
- Automatic (default). Flux's native end-of-turn detection decides when a turn ends. EndOfTurn events carry "trigger": "model" . Nothing changes for existing integrations. Semi-manual. Keep Flux's detection running, but override it whenever you have a definitive signal , a push-to-talk release, a DTMF tone, a "send" tap , by sending a ForceEndTurn .
Switch modes mid-stream , even per turn
Because eot_threshold can be updated live with a Configure message, you can change turn-taking behavior for exactly the turn that needs it and then change back. For example, when a caller is about to read an 8-character alphanumeric account ID, raise eot_threshold to 1.0 so Flux won't cut them off between characters, end the turn yourself once you've...
What's new - Flux
ForceEndTurn message. Send {"type": "ForceEndTurn"} as a WebSocket text frame to end the active turn immediately. Flux ends the turn on the audio transcribed so far and emits a standard EndOfTurn . See Force End Turn . trigger field on EndOfTurn .
What's new - Voice Agent
The Voice Agent API provides the same turn-taking control through the ForceEndTurn client message when the agent uses the Flux ( v2 ) listen provider. Send it to end the current user turn immediately, or set agent.listen.provider.eot_threshold=1.0 to fully suppress natural end-of-turn detection and drive every turn ending with ForceEndTurn .
Nova-3 Model Improvements for Bulgarian, Croatian, Estonian, Georgian, Italian, Latvian, Lithuanian, Malay, Marathi, and Telugu
We have released improved Nova-3 monolingual models for ten existing languages. These updates enhance transcription quality for batch and streaming workloads.
Nova-3 Adds Assamese, Mongolian, and Pashto, Plus Improved Models for Czech, Danish, Swedish, Tagalog, and Turkish
We have added Assamese, Mongolian, and Pashto as new Nova-3 languages and released improved Nova-3 monolingual models for several existing languages. These updates expand language coverage and enhance transcription quality for batch and streaming workloads.
🆕 New languages
- Assamese ( as , as-IN ) , available for batch and streaming. Mongolian ( mn ) , available for batch and streaming. Pashto ( ps , ps-AF ) , available for batch and streaming. Access these languages by setting model="nova-3" and the relevant language code in your request.