> 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.

# August 12, 2026

> Deepgram Self-Hosted release 260812 brings Flux TTS to self-hosted deployments in Early Access on the new /v2/speak endpoint, and adds Nova-3 support for Nepali and Punjabi.

## Deepgram Self-Hosted August 2026 Release (260812)

### Container Images (release 260812)

* `quay.io/deepgram/self-hosted-api:release-260812`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-api:1.192.25`

* `quay.io/deepgram/self-hosted-engine:release-260812`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-engine:3.127.0`

  * Minimum required NVIDIA driver version: `>=570.172.08`

* `quay.io/deepgram/self-hosted-license-proxy:release-260812`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-license-proxy:1.11.0`

* `quay.io/deepgram/self-hosted-billing:release-260812`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-billing:1.14.0`

### FIPS 140-3 Images

FIPS 140-3 images are available for all four self-hosted services, published under the `-fips` tag suffix:

* `quay.io/deepgram/self-hosted-api:release-260812-fips`
* `quay.io/deepgram/self-hosted-engine:release-260812-fips`
* `quay.io/deepgram/self-hosted-license-proxy:release-260812-fips`
* `quay.io/deepgram/self-hosted-billing:release-260812-fips`

These images run OpenSSL's FIPS 140-3 validated cryptographic provider. Enable FIPS by setting `[fips] mode = "enabled"` in each service's configuration. FIPS mode should be enabled only on the `-fips` images; the standard images do not include the FIPS provider. See [FIPS-Compliant Deployment](/docs/fips-compliant-deployment) for setup and configuration details.

**Known issue: MP3 and FLAC output are not available on FIPS images.** A text-to-speech request that asks for either format returns `HTTP 200` with an empty body rather than an error. `/v1/speak` and batch `/v2/speak` both return MP3 by default, so set `encoding` explicitly on FIPS images. `linear16` and `opus` output are unaffected, as is streaming `/v2/speak`.

This limits audio *output* only. Sending MP3 or FLAC *input* to speech-to-text on a FIPS image is unaffected.

See [MP3 and FLAC Output](/docs/fips-compliant-deployment#mp3-and-flac-output) for details and workarounds.

### Flux TTS (Early Access)

Flux TTS, Deepgram's streaming-first speech synthesis model, is now available in self-hosted deployments as an Early Access feature. Flux TTS is served on the new `/v2/speak` endpoint, which offers both a batch REST transport and a real-time WebSocket transport. Aura and Aura-2 continue to be served on `/v1/speak` and are unchanged.

Flux TTS is off by default. Enabling it requires a dedicated Engine and GPU — Flux TTS and Aura cannot share an Engine, and Flux TTS workers bind to a single GPU — plus a Flux TTS model file, which you can request from your Deepgram account representative. See [Deploying Flux TTS](/docs/deploy-flux-tts) for configuration, deployment constraints, and test requests.

For the model, voices, and API surface, see the [Flux TTS Overview](/docs/flux-tts/overview) and the [`/v2/speak` API reference](/reference/text-to-speech/speak-flux).

### This Release Contains The Following Changes

* **Flux TTS (Early Access)** — Flux TTS is now available in self-hosted deployments on the new `/v2/speak` endpoint. See [Deploying Flux TTS](/docs/deploy-flux-tts) for setup, and the section above for details.
* **Nepali and Punjabi Support** — Nova-3 monolingual models now support Nepali (`ne`) and Punjabi (`pa`, `pa-IN`), in both batch and streaming. See [the full announcement](/changelog/2026/8/5) for details.
* **General Improvements** — dependency and security updates, and refreshed base images.