> 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 240426)

- `deepgram/onprem-api:release-240426`
  - Equivalent image tag to `deepgram/onprem-api:1.116.3`


- `deepgram/onprem-engine:release-240426`
  - Equivalent image tag to `deepgram/onprem-engine:3.68.12`
  - Minimum required NVIDIA driver version: `>=525.60.13`


- `deepgram/onprem-license-proxy:release-240426`
  - Equivalent image tag to `deepgram/onprem-license-proxy:1.6.0`


- `deepgram/onprem-billing:release-240426`
  - Equivalent image tag to `deepgram/onprem-billing:1.9.0`


- `deepgram/onprem-dgtools:release-240426`
  - Equivalent image tag to `deepgram/onprem-dgtools:2.1.7`



### This Release Contains The Following Changes

- Adds support for Aura text-to-speech (TTS) on a new `speak/` endpoint! 🗣️
  - Reach out to your Deepgram account representative to receive new models to use TTS.


- Improves entity formatting.
- Improves intelligence features (sentiment, intents, topics, summarization).
- Lengthens the default streaming timeout from 10 seconds to 12 seconds, to align with Deepgram's hosted API.
- Adds configuration value (`max_concurrently_loaded_models)` to set an upper limit on the number of models loaded into memory, to mitigate memory errors and performance issues.
- Stability improvements, security patches, and bug fixes. 🐛