feat(eot): Audio EOT

[chenghao-mou]

Adds streaming audio end-of-turn detection. Single user-facing AudioTurnDetector that selects between two backends:

• cloud
• local

On cloud transport error or predict_end_of_turn timeout, the session swaps to local for the rest of the stream (sticky per session, one warning per failure mode). Local failures emit the default 1.0 prediction and retry on the next turn.

A user-set unlikely_threshold is scaled multiplicatively against the cloud default so the operating point survives a fallback.

Wired into AudioRecognition: VAD INFERENCE_DONE triggers warmup, END_OF_SPEECH activates the stream, predictions flow back through _run_eou_detection and arbitrate against the endpointing delay. A speaking guard cancels an in-flight bounce if VAD START_OF_SPEECH fires mid-window.

[hsjun99]

@chenghao-mou Excited to see this! A couple of questions:

1. Will the multimodal EOT model be publicly accessible via model weights or agent-gateway.livekit.cloud, or in some other way?
2. Any rough timeline for when MultiModalTurnDetector gets fully wired up?

[chenghao-mou]

@chenghao-mou Excited to see this! A couple of questions:

1. Will the multimodal EOT model be publicly accessible via model weights or agent-gateway.livekit.cloud, or in some other way?
2. Any rough timeline for when MultiModalTurnDetector gets fully wired up?

Thanks for your patience! We don't have an official decision or timeline yet, but hopefully I can get it ready within a month or two.