Releasesby GlyphIntroducing Flux: Conversational Speech Recognition to Solve the Biggest Problem in Voice Agents – Interruptions
Flux is here: the first real-time Conversational Speech Recognition model built for voice agents. Solve interruptions, cut latency, and ship natural conversations faster than ever. Deepgram is proud to announce the release of Flux , the first speech recognition model that knows when someone is actually done talking.
Also shipped Oct 2, 2025Deepgram in October 2025 →
Bring your Vercel project to Replit (in minutes)
Users can now import Vercel projects into Replit. The Replit Agent automates the setup process, including environment variable configuration and deployment.
Cloudflare Fundamentals, Access - Fine-grained Permissioning for Access for Apps, IdPs, & Targets now in Public Beta
Fine-grained permissions for Access Applications, Identity Providers (IdPs), and Targets is now available in Public Beta. This expands our RBAC model beyond account & zone-scoped roles, enabling administrators to grant permissions scoped to individual resources. What's New Access Applications ↗ : Grant admin permissions to specific Access Applications.
Updated support for OpenAI GPT-OSS (gpt-oss-120b) - Tool calling with strict: true (constrained decoding) -...
Updated support for OpenAI GPT-OSS (gpt-oss-120b) Tool calling with strict: true (constrained decoding) Response format with json_schema when using strict=true Response format with json_object when using strict=true tool_choice: none Updated JSON Schema limitations: Nested levels increases from 5 to 10 Max properties increases from 100 to 500 Enabled...
Workers AI - New Deepgram Flux model available on Workers AI
Deepgram's newest Flux model @cf/deepgram/flux is now available on Workers AI, hosted directly on Cloudflare's infrastructure. We're excited to be a launch partner with Deepgram and offer their new Speech Recognition model built specifically for enabling voice agents. Check out Deepgram's blog ↗ for more details on the release.
Workers Analytics Engine, Workers - Workers Analytics Engine adds supports for new SQL functions
You can now perform more powerful queries directly in Workers Analytics Engine ↗ with a major expansion of our SQL function library. Workers Analytics Engine allows you to ingest and store high-cardinality data at scale (such as custom analytics) and query your data through a simple SQL API.
Issue discussion summaries
Discussion summaries now appear on issues with substantial activity. Read these summaries to understand what's happened in an issue without reading every comment. Summaries capture decisions, blockers, debates and their resolutions, and key people involved. When new comments are posted, summaries automatically regenerate to reflect changes.
More from DeepgramEvery Deepgram release →
Container Images (release 250929)
- quay.io/deepgram/self-hosted-api:release-250929 Equivalent image to: quay.io/deepgram/self-hosted-api:1.159.2 quay.io/deepgram/self-hosted-engine:release-250929 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.104.3 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-250929 Equivalent image to...
This Release Contains The Following Changes
⚠️ Important : Please refrain from using this release version if you run Nova-3 diarization. General Improvements , Keeps our software up-to-date.
Add Any MCP Server from Smithery in Seconds
No more JSON config headaches. Saga now integrates directly with the Smithery MCP directory , letting you add any MCP server with just a few clicks. Browse the complete Smithery directory and when you find an MCP server you want to use, simply click "Deepgram Saga" > "One-Click Install" and it's instantly configured and ready to go.
Container Images (release 251015)
- quay.io/deepgram/self-hosted-api:release-251015 Equivalent image to: quay.io/deepgram/self-hosted-api:1.166.0 quay.io/deepgram/self-hosted-engine:release-251015 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-251015 Equivalent image to...
This Release Contains The Following Changes
- Adds support for Flux , our new turn-based streaming speech-to-text model! Flux is purpose-built for voice agent use-cases. Because of its resource usage, Flux must be run in its own self-hosted deployment separate from any other Deepgram models, even other speech-to-text models like Nova-3.
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...
Containerized Audio Support
Flux now also accepts containerized audio formats, eliminating the need to manually specify encoding and sample rate parameters: WAV containers with linear16 encoding Ogg containers with opus encoding When sending containerized audio, omit the encoding and sample_rate parameters, Flux will automatically detect these from the container metadata.