03Conversation
End of turn
Answer quickly when the caller is done, and wait when they're only pausing.
End-of-turn detection decides when the caller has finished speaking. Too eager and the agent talks over people mid-thought. Too cautious and every reply starts with dead air. It is the largest controllable part of TTFB.
turns:
controller: turn-1-mini
# threshold: 0.36 end-of-turn probability needed
# min_silence: 60 ms of quiet before the model may decide
# max_silence: 1500 ms after which the turn ends regardlessControllers
| Value | How it decides | Languages | Best for |
|---|---|---|---|
turn-1-mini | A streaming model scores every 20 ms whether the turn is over. In our tests it answers about 140 ms after the caller stops and holds through "um, so…" pauses. | English | The default. |
smart-turn | At each pause of min_silence ms (default 200), Smart Turn v3 judges whether the speaker sounds done. | Multilingual | Non-English calls. |
vad | Fixed silence: the turn ends after min_silence ms (default 500). | Any | Predictability over naturalness. |
maai | MaAI Voice Activity Projection from both voices. Also decides interruptions. | English | Full-duplex experiments. |
Tuning
| Field | Default (turn-1-mini / smart-turn / vad) | Raise it to… | Lower it to… |
|---|---|---|---|
threshold | 0.36 / 0.5 / – | cut people off less | answer faster |
min_silence | 60 / 200 / 500 ms | ignore short breaths | react sooner |
max_silence | 1500 ms | wait for slow, thoughtful speakers | never leave dead air |
Tune against real calls. In the dashboard's latency tab, vad_tail is the
silence the model needed. Premature counts replies that were cancelled before any audio played,
because the caller kept talking. Lower threshold until premature turn ends start
to appear, then step back.
Why finalize matters
When the controller fires turn_end, Cuelo asks the STT to finalize: flush
a final transcript right away instead of waiting for the provider's own
endpointing, which is slower. That's the finalize
stage in the latency breakdown, typically 50–150 ms. Every STT provider in
Cuelo implements it.
Pairing with backchannels
End-of-turn models often fire on the pause right after the agent says "mhm".
backchannel_hold makes the agent wait before taking that turn. See
Backchannels.