> 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.

# June 30, 2026

> Deepgram Self-Hosted release 260630 adds Flux word-level timestamps, a Spanish number formatting fix, additional number and currency formatting, streaming timestamp accuracy fixes, and a restructured self-hosted models endpoint response.

## Deepgram Self-Hosted June 2026 Release (260630)

### Container Images (release 260630)

* `quay.io/deepgram/self-hosted-api:release-260630`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-api:1.192.3-1`

* `quay.io/deepgram/self-hosted-engine:release-260630`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-engine:3.119.1-1`

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

* `quay.io/deepgram/self-hosted-license-proxy:release-260630`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-license-proxy:1.10.1-2`

* `quay.io/deepgram/self-hosted-billing:release-260630`
  * Equivalent image to:
    * `quay.io/deepgram/self-hosted-billing:1.13.0`

### Breaking Change: `GET /v1/models` Response Format

The self-hosted `GET /v1/models` endpoint now lists every loaded model, not just core speech-to-text (Nova) models. The response now also includes Text-to-Speech (Aura voice packs and voices) and helper models (entity detection/NER, diarization), groups results by model type, and indicates batch versus streaming mode for each speech-to-text model.

As part of this change, the response shape changes from a flat list to an object grouped by model type. Any integration that parses the `/v1/models` response must be updated to handle the new structure **before** upgrading to `release-260630`. See [Model Metadata](/docs/model-metadata) for the current response format.

### This Release Contains The Following Changes

* **Flux Word-Level Timestamps** — each word in the `words` array now includes `start` and `end` times on the Flux streaming endpoint (`/v2/listen`). This is an additive change. If your client library rejects unrecognized response fields, update to a current SDK version — for the Deepgram Python SDK, use `6.0.1` or later, or `5.3.4` if you are on the `5.x` line. See [Flux Feature Overview](/docs/flux/feature-overview) for details.
* **Spanish Number Formatting Fix** — "veintiuno" now correctly formats as `21` in Spanish transcripts (Nova-3 and Nova-2, including multilingual).
* **Additional Number and Currency Formatting** — numeral expansion now applies to Flux multilingual transcripts; Romanian and Russian ordinal suffixes are supported; and currency (for example, `Bn$`, `Mn$`, `Tn$`, `Th$`) and fiscal-quarter expressions format more consistently.
* **Streaming Timestamp Accuracy** — corrected utterance timestamp ordering and improved word `start` and `end` time accuracy on streaming requests.
* **General Improvements** — Keeps our software up-to-date.