Releasesby GlyphNova-3 Model Update
🎯 Nova-3 supports 11 new languages We've added support for 11 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 language support beyond English.
Also shipped Nov 4, 2025Deepgram in November 2025 →
Google Workspace Inbound User Directory Sync Beta
We’re excited to introduce Google Workspace User Directory Sync, now available as part of our Beta program. This feature allows organizations to automatically synchronize users from their Google Workspace directory into Auth0 - ensuring user data stays accurate and up to date without relying on login events.
Analytics Buckets in Public Alpha
Supabase Analytics Buckets are now in Public Alpha and can be managed from the dashboard, enabling users to store large datasets for analytics and reporting alongside other project storage.
Log Explorer now supports query cancellation
We're excited to announce that Log Explorer users can now cancel queries that are currently running. This new feature addresses a common pain point: waiting for a long, unintended, or misconfigured query to complete before you can submit a new, correct one.
Log Explorer now shows query result distribution
We're excited to announce a new feature in Log Explorer that significantly enhances how you analyze query results: the Query results distribution chart. This new chart provides a graphical distribution of your results over the time window of the query. Immediately after running a query, you will see the distribution chart above your result table.
Fine Grained Access for Logs
As your organization scales, managing who can access specific log data is vital for security, compliance, and data governance. Your security teams may need to monitor critical logs that contain sensitive information (PII), while development teams should only see logs relevant to their specific services.
Synthetic Monitoring: Alert Routing Summary
Understanding where your alerts are routed just got a whole lot easier. When configuring per-check alerts in Grafana Cloud Synthetic Monitoring, you can now see exactly which notification policies your alerts match, right from the UI.
More from DeepgramEvery Deepgram release →
Legacy Intelligence Features Deprecated
We have deprecated several legacy Intelligence feature parameters. As of today, requests using these legacy parameters will return HTTP 400 errors. Please update your implementation to use the current parameters.
Documentation Resources
- Sentiment Analysis Topic Detection Summarization For questions or support, please reach out through our developer support channels.
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 detect and transcribe a much broader array of languages with one request. Enable broader coverage by setting detect_language=true in your API call.
Entity Detection Now Available for Streaming Speech-to-Text
We're excited to announce that Entity Detection is now available for streaming (real-time) speech-to-text with Nova 3, Nova 2, Nova, and Enhanced models. detect_entities=true Previously available only for pre-recorded audio, you can now identify and extract over 50 unique entity types in real-time streaming transcriptions, including email addresses, names...
Container Images (release 251029)
- quay.io/deepgram/self-hosted-api:release-251029 Equivalent image to: quay.io/deepgram/self-hosted-api:1.167.1 quay.io/deepgram/self-hosted-engine:release-251029 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.104.7 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-251029 Equivalent image to...
This Release Contains The Following Changes
- General Improvements , Keeps our software up-to-date.
Use Deepgram's Managed Cartesia TTS Models
We're excited to announce an easier way to use Cartesia's Text-to-Speech models inside Deepgram's voice agent – Deepgram-managed Cartesia models . Similar to our managed LLM's , simply specify Cartesia as your model provider and the correct model name to get started instantly.
🤖 Claude Haiku 4.5 LLM Support
We've added support for Anthropic's new Claude Haiku model in our Voice Agent API! Implementation: Configure your chosen model in your Voice Agent settings: { "type": "Settings", "agent": { "think": { "provider": { "type": "anthropic", "model": "claude-haiku-4-5" } } } } For complete information about supported LLMs including Claude Haiku 4.5, visit our...