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

#### 0.9.3-1

Point release

## Adding Voxist as new STT Vendor, ElevenLanbs Conversational AI Agents and more

1. Adds support for Voxist STT.
   \
   \
   [PR](https://github.com/jambonz/jambonz-feature-server/pull/1066)

2. Enhance TTS caching to account for the model of the TTS engine as well as vendor and other properties.
   \
   \
   [PR](https://github.com/jambonz/jambonz-feature-server/pull/1062), [Issue](https://github.com/jambonz/jambonz-feature-server/issues/1059)

3. Adds support for using ElevenLabs conversational AI agents.
   \
   \
   [PR](https://github.com/jambonz/jambonz-feature-server/pull/1052), [PR](https://github.com/jambonz/jambonz-feature-server/pull/1063)

4. Adds support for setting the speech recognition mode for Azure STT.  The allowed values are
   CONVERSATION, DICTATION and INTERACTIVE.
   \
   \
   [PR](https://github.com/jambonz/jambonz-feature-server/pull/1060), [Issue](https://github.com/jambonz/jambonz-feature-server/issues/1057)

5. Fixes an issue where a re-INVITE received during a [dial](/verbs/verbs/dial) operation could cause an exception.
   \
   \
   [PR](https://github.com/jambonz/jambonz-feature-server/pull/1054), [Issue](https://github.com/jambonz/jambonz-feature-server/issues/1053)

6. Adds support for streaming TTS using Rime Labs.
   \
   \
   [PR](https://github.com/jambonz/jambonz-feature-server/pull/1047)

7. Supports fetching elevenlabs models by api-key.
   \
   \
   [PR](https://github.com/jambonz/jambonz-api-server/pull/383)

8. Fixes some issues with tracking call counts on the SBC.
   \
   \
   [PR](https://github.com/jambonz/sbc-inbound/pull/189)