Introducing Flux: Conversational Speech Recognition to Solve the Biggest Problem in Voice Agents – Interruptions
UpdateUnverifiedAdded Sep 24, 2026
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.
Topics: AI agents, Streaming, Data integration, Observability, Developer tools
More Deepgram releases
Every Deepgram release| Date | Release | Type |
|---|---|---|
| Oct 2 | Availabilityunverified Update | Update |
| Sep 29 | Container Images (release 250929)unverified Update | Update |
| Sep 29 | This Release Contains The Following Changesunverified Update | Update |
| Sep 26 | Add Any MCP Server from Smithery in Secondsunverified Update | Update |
| Oct 15 | Container Images (release 251015)unverified Update | Update |
| Oct 15 | This Release Contains The Following Changesunverified Update | Update |
| Oct 16 | Flux: Expanded Audio Format Supportunverified Update | Update |
| Oct 16 | Raw Audio Format Supportunverified Update | Update |
Also shipped on Oct 2, 2025
Deepgram in October 2025
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.