Turn-taking

Good turn-taking is most of what makes an agent feel human: not cutting people off, not leaving long silences, and stopping when interrupted. These settings live on the flow's Behaviour tab; from code, send them in runtime. They apply from the next session.

1await voxio.flows.update(flowKey, {
2  runtime: {
3    "process-type": "speech-native",
4    "speaker-turn-timeout-ms": 500,
5    "pre-fire": true,
6  },
7});

#Conversation engine

process-typestring

Conversation engine. How the agent decides the caller has finished. Hover each option to compare. One of: speech-native (Listens to how the caller speaks to know when they’ve finished, and can start replying early.), stt-native (Waits for the finished transcript before replying. Simpler, a little slower.). Default: "stt-native".

warmup-agentboolean

Warm up before the call. Makes the first reply faster. Default: false.

first-chunk-fastboolean

Speak the first words immediately. Start talking as soon as the first words are ready. Default: false.

#When the agent replies

pre-fireboolean

Reply early. Starts answering before the silence ends; undone if the caller keeps talking. Default: false.

pre-fire-configobject

Early-reply window. How early the agent may start replying; it adapts between the shortest and longest. Only used when pre-fire is on. Fields: current (Start at, ms), min (Shortest, ms), max (Longest, ms). Default: {"min":50,"max":5000,"current":100}.

streaming-grace-msnumber (ms)

Hold the floor after replying. A late “uh” in this window isn’t treated as a new turn. From 0 to 5000. Default: 250.

speaker-turn-timeout-msnumber (ms)

Caller’s pause before replying. How long the caller can pause before the agent answers. From 100 to 5000. Default: 600.

vad-thresholdnumber

Voice detection sensitivity. Higher ignores background noise. Web calls only. Web sessions only. From 0 to 1. Default: 0.5.

#Tuning

#Next steps

• Interruptions: what happens when the caller talks over the agent.
• When the caller goes quiet: nudges.