Stream realtime TTS audio as it is synthesized

2026-09-16 14:55:12 +02:00
parent 97c8072b3d
commit 3f684b7325
3 changed files with 60 additions and 31 deletions
@@ -12,6 +12,13 @@ WebRTC; Athena transcribes it; the service asks OpenClaw to run
 connection. This is a half-duplex prototype. Barge-in and remote-network TURN
 support are not implemented.

+For replies, the bridge consumes Athena's existing
+`/v1/audio/speech/pcm-stream` endpoint (24 kHz mono PCM) and enqueues audio
+frames as they arrive. Playback can start before Qwen finishes synthesizing a
+long reply. The bounded queue applies backpressure instead of truncating long
+audio, and the next turn waits until all frames have played. The two-turn
+WebRTC test verifies that audio begins before the fake PCM stream finishes.
+
 The bridge announces each committed user audio item before sending its completed
 transcript with the same item ID. OpenClaw requires that sequence to persist the
 transcript; omitting the item caused “Realtime transcript refers to an unknown