hailin
/
it0
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(voice): randomly pick thinking sound from all 7 built-in clips per session 

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
hailin 2026-03-09 06:56:31 -07:00
parent 38bea33074
commit afc1ae6fbe
1 changed files with 14 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
packages/services/voice-agent/src/agent.py
View File

@ -387,16 +387,21 @@ async def entrypoint(ctx: JobContext) -> None:
_cleanup_ref.append(_on_room_disconnect) _cleanup_ref.append(_on_room_disconnect)
# --- Thinking state audio feedback --- # --- Thinking state audio feedback ---
# BackgroundAudioPlayer listens for AgentStateChangedEvent from the # Randomly pick one of all available built-in clips each session.
# session. When state transitions to "thinking" (STT done, waiting for _all_clips = [
# LLM response), it plays the built-in keyboard typing sound through BuiltinAudioClip.KEYBOARD_TYPING,
# the LiveKit audio track. The sound stops automatically when the agent BuiltinAudioClip.KEYBOARD_TYPING2,
# enters "speaking" state (TTS begins). This gives the user audible BuiltinAudioClip.OFFICE_AMBIENCE,
# feedback that the AI is processing their request. BuiltinAudioClip.CITY_AMBIENCE,
# Available built-in clips: KEYBOARD_TYPING, KEYBOARD_TYPING2, BuiltinAudioClip.FOREST_AMBIENCE,
# OFFICE_AMBIENCE, CITY_AMBIENCE, FOREST_AMBIENCE, CROWDED_ROOM, HOLD_MUSIC BuiltinAudioClip.CROWDED_ROOM,
BuiltinAudioClip.HOLD_MUSIC,
]
import random as _random
_chosen_clip = _random.choice(_all_clips)
logger.info("Thinking sound this session: %s", _chosen_clip)
bg_audio = BackgroundAudioPlayer( bg_audio = BackgroundAudioPlayer(
thinking_sound=BuiltinAudioClip.KEYBOARD_TYPING, thinking_sound=_chosen_clip,
) )
await bg_audio.start(room=ctx.room, agent_session=session) await bg_audio.start(room=ctx.room, agent_session=session)