Releasesby GlyphContainer 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...
Also shipped Oct 29, 2025Deepgram in October 2025 →
How Deno and Prisma Partnered to Power Per-Branch Databases
Deno Deploy now integrates Prisma Postgres to provide instant per-branch databases. This enables developers to automate database provisioning for full-stack deployments.
Tailscale Peer Relays
- New: Use Tailscale Peer Relays for client-to-client connections when direct connections aren't possible ( beta ).
Visual policy editor (GA)
- Changed: Use the visual policy editor to create and manage your tailnet policy file ( generally available ).
Automate your searches with Scheduled Search and Reporting (Preview)
Stop running the same NRQL queries over and over. Whether you're checking daily failed transactions or monitoring failures in your log data, manual reporting is time-consuming and makes it easy to miss insights. We're excited to introduce Scheduled Search and Reporting (Preview) .
Native Histograms are Generally Available
We are thrilled to announce that Native Histograms are now generally available (GA)! This milestone comes after three years of dedicated development, bringing a powerful data type to Prometheus users. Native histograms improve histogram resolution without requiring users to adjust the buckets.
Multiple tailnets for a single organization
- New: Administer multiple tailnets ( alpha ) under a single organization, using a common identity provider and domain.
More from DeepgramEvery Deepgram release →
This Release Contains The Following Changes
- General Improvements , Keeps our software up-to-date.
Nova-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.
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...
Flux: Expanded Audio Format Support
Flux now supports a wider range of audio formats beyond linear16 , giving you more flexibility in how you send audio to our conversational speech recognition model. This update adds support for additional raw audio encodings and containerized audio formats.
Raw Audio Format Support
Flux now accepts the following raw (non-containerized) audio encodings: linear16 - 16-bit signed little-endian PCM (existing) linear32 - 32-bit signed little-endian PCM (new) mulaw - Mu-law encoding (new) alaw - A-law encoding (new) opus - Opus codec (new) ogg-opus - Opus in Ogg container (new) When using raw audio formats, you must specify both the...