> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.deepgram.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.deepgram.com/_mcp/server.

# October 15, 2025

> Deepgram Self-Hosted release 251015 adds Flux conversational STT model support via the /v2/listen endpoint and resolves a Nova-3 diarization regression for API 1.166.0 and Engine 3.104.7.

## Deepgram Self-Hosted October 2025 Release (251015)

### 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:
    * `quay.io/deepgram/self-hosted-license-proxy:1.9.1`

* `quay.io/deepgram/self-hosted-billing:release-251015`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-billing:1.12.1`

### This Release Contains The Following Changes

* Adds support for [Flux](https://flux.deepgram.com), 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.
  * Connect to Flux's new `/v2/listen` endpoint using `model=flux-general-en`, such as: `http://localhost:8080/v2/listen?model=flux-general-en`. Do not pass an additional `language` parameter.
  * Flux is currently English-only.
  * Contact your Deepgram account representative for access to the Flux model.
  * Get started with Flux's [developer docs](https://developers.deepgram.com/docs/flux/quickstart) and [API reference](https://developers.deepgram.com/reference/speech-to-text/listen-flux).
  * Learn more in Flux's [changelog entry](https://developers.deepgram.com/changelog/speech-to-text-changelog#introducing-flux-conversational-speech-recognition-to-solve-the-biggest-problem-in-voice-agents--interruptions), [Announcement Blog](https://deepgram.com/learn/introducing-flux-conversational-speech-recognition), and try our [Interactive Demo](https://flux.deepgram.com).
  * To enable Flux in your self-hosted deployment, make the following additions to your TOML files:
    * api.toml:
      ```
      [features]
      listen_v2 = true
      ```
    * engine.toml:
      ```
      [flux]
      enabled = true
      ```

* Resolves a Nova-3 diarization issue present in the prior release (`release-250929`).

* **General Improvements** — Keeps our software up-to-date.