Send AI TTS audio to live caller during auto-respond
The auto-respond function played AI TTS to the local Loopback channel but didn't send it over WebSocket to the live caller in the browser. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1022,6 +1022,13 @@ async def _check_ai_auto_respond(real_caller_text: str, real_caller_name: str):
|
||||
)
|
||||
thread.start()
|
||||
|
||||
# Also send to active real caller so they hear the AI
|
||||
if session.active_real_caller:
|
||||
caller_id = session.active_real_caller["caller_id"]
|
||||
asyncio.create_task(
|
||||
caller_service.send_audio_to_caller(caller_id, audio_bytes, 24000)
|
||||
)
|
||||
|
||||
|
||||
# --- Follow-Up & Session Control Endpoints ---
|
||||
|
||||
|
||||
Reference in New Issue
Block a user