(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
+2
View File
@@ -12,6 +12,8 @@ dependencies = [
"protobuf==6.33.6",
"minio==7.2.20",
"sentry-sdk==2.66.1",
"websockets==17.1",
"httpx==0.28.1",
]
[project.optional-dependencies]