Skip to content

This Release Contains The Following Changes

UpdateUnverifiedAdded Sep 24, 2026

- 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.

Topics: AI agents, LLMs, Streaming, Observability, Developer tools

Deepgram's release notes

More Deepgram releases

Every Deepgram release
DateRelease
Oct 15Container Images (release 251015)unverified
Update
Oct 16Flux: Expanded Audio Format Supportunverified
Update
Oct 16Raw Audio Format Supportunverified
Update
Oct 16Containerized Audio Supportunverified
Update
Oct 16Supported Sample Ratesunverified
Update
Oct 16Implementationunverified
Update
Oct 2Introducing Flux: Conversational Speech Recognition to Solve the Biggest Problem in Voice Agents – Interruptionsunverified
Update
Oct 2Availabilityunverified
Update

Also shipped on Oct 15, 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.

New releases by email

Tuesday mornings: the week's data, AI and developer-tools releases, only in weeks when something shipped.

Double opt-in. Unsubscribe any time.