> 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.

## Container Images (release 250331)

- `quay.io/deepgram/self-hosted-api:release-250331`
  - Equivalent image to:
    - `quay.io/deepgram/self-hosted-api:1.141.0`
    - `quay.io/deepgram/onprem-api:release-250331`
    - `quay.io/deepgram/onprem-api:1.141.0`

- `quay.io/deepgram/self-hosted-engine:release-250331`
  - Equivalent image to:
    - `quay.io/deepgram/self-hosted-engine:3.85.4`
    - `quay.io/deepgram/onprem-engine:release-250331`
    - `quay.io/deepgram/onprem-engine:3.85.4`


  - Minimum required NVIDIA driver version: `>=530.30.02`
  - Maximum required NVIDIA driver version: `<=561.00.00`

- `quay.io/deepgram/self-hosted-license-proxy:release-250331`
  - It is **essential to upgrade the license proxy** before upgrading the API or Engine for this release. Neglecting to upgrade the license proxy will cause a breaking change on deployment.
  - Equivalent image to:
    - `quay.io/deepgram/self-hosted-license-proxy:1.8.0`
    - `quay.io/deepgram/onprem-license-proxy:release-250331`
    - `quay.io/deepgram/onprem-license-proxy:1.8.0`

- `quay.io/deepgram/self-hosted-billing:release-250331`
  - Equivalent image to:
    - `quay.io/deepgram/self-hosted-billing:1.11.2`
    - `quay.io/deepgram/onprem-billing:release-250331`
    - `quay.io/deepgram/onprem-billing:1.11.2`

### This Release Contains The Following Changes

- Adds support for our new class of [multilingual Nova-3](https://deepgram.com/learn/introducing-nova-3-speech-to-text-api) models.
  - Use `model=nova-3&language=multi`.
  - Contact your Deepgram account representative for access to Nova-3.
- Significantly improves formatting for all transcripts, including in multilingual contexts. This new formatting is powered by a dedicated Named Entity Recognition (NER) model that performs sophisticated recognition of entities, including phone numbers, addresses, and dates, in order to return excellent formatted transcripts. NER is required for smart-formatted Nova-3 transcripts, and strongly suggested for all other speech-to-text transcripts.
  - Consult our [instructions for enabling NER formatting](https://deepgram.gitbook.io/help-center/self-hosted/how-can-i-enable-ner-formatting-in-my-self-hosted-deployment) to make required updates to configuration as well as models.
  - Improvements to smart-formatting have modified the formatting of some entity classes. Please contact your Deepgram account representative if you have any questions.
- Improves streaming smart-formatting.
- Improves non-English numeral formatting.
- Resolves an issue with Simplified Chinese (`zh`/`zh-CN`) language requests.
- Keeps our software up-to-date.

**Reminder**: The Deepgram image repositories have been updated to reflect our "self-hosted" naming. Images should now be pulled from the `self-hosted-*` Quay repositories. For the next six months, both `onprem-*` and `self-hosted-*` image repositories will receive identical image updates monthly, and we will announce image tags in the `self-hosted` repositories. Subsequently, we will only publish new images to `self-hosted-*` repos, deprecating `onprem-*` repository variants.