✨(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.

compose.yml

@@ -251,6 +251,7 @@ services:
     build:
       context: ./src/agents
       target: development
+    command: ["python", "multi_user_transcriber.py", "dev"]
     env_file:
       - env.d/development/multi_user_transcriber
     volumes: