(agent) support Voxtral realtime as inference engine

The Kyutai open-source model turned out not to be production-ready:
it caused disruptions in the production environment, especially on
long-running meeting sessions.

Switch to the Voxtral realtime model, which looks like a
credible competitor and behaves much better in our setup.

For now, the code handling the Voxtral realtime API lives directly
in the project. It could be extracted into an open-source package
later.

See PR #1277 for the full details of the implementation, proposed
by @cameldev.
This commit is contained in:
leo
2026-05-19 18:35:25 +02:00
committed by aleb_the_flash
parent c7e3168ba3
commit 0a0cdae896
8 changed files with 1328 additions and 539 deletions
+4
View File
@@ -8,6 +8,10 @@ and this project adheres to
## [Unreleased]
### Added
- ✨(agent) support Voxtral realtime as inference engine
### Changed
- 🔥(backend) remove the S3 storage-event webhook for recordings