Skip to content

docs(livekit-voice-agent): add word_timestamps opt-in to TTS example #58

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
harshitajain165 wants to merge 4 commits into
base: main
Choose a base branch
from
Open

docs(livekit-voice-agent): add word_timestamps opt-in to TTS example #58

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1f3a275
docs(livekit-voice-agent): add word_timestamps opt-in comment to TTS …
harshitajain165 Jun 1, 2026
ddb1702
fix(livekit-voice-agent): correct word_timestamps comment direction
harshitajain165 Jun 3, 2026
2379342
fix(livekit-voice-agent): restore word_timestamps=True as opt-in comment
harshitajain165 Jun 3, 2026
b57e2f6
fix(livekit-voice-agent): replace stale CrewSession with AgentSession
harshitajain165 Jun 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion voice-agents/livekit-voice-agent/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,12 +106,13 @@ tts=smallestai.TTS(
model="lightning_v3.1_pro",
voice_id="meher",
language="en",
# word_timestamps=True, # opt in to per-word timing events (base-queue EN/HI voices)
)
```

### Interruption — Zero Custom Code

The `CrewSession` handles interruptions automatically. When Silero VAD detects you speaking mid-response, the TTS stream is cancelled and your speech is processed as a new turn.
The `AgentSession` handles interruptions automatically. When Silero VAD detects you speaking mid-response, the TTS stream is cancelled and your speech is processed as a new turn.

---

Expand Down