Listens while it talks

Full duplex

People talk over each other, say “mm-hm”, and change their minds mid-sentence. A full-duplex agent keeps listening the whole call, including while it is speaking.

Turn detection
23 languages
Interruptions
Tunable
Listening cues
Pre-synthesized
  1. Listening
  2. Thinking
  3. Speaking
Turn-taking

What happens when they interrupt

The same moment in a call: the caller cuts in while the agent is answering.

Turn-taking mode
Caller
Agent
mm-hm
What happens
stops, listens
The agent says “mm-hm” while the caller is still talking, stops the moment it is interrupted, and answers what it just heard.
Live demo

Try to talk over it

Interrupt this agent halfway through a sentence. Say “wait”. It should stop, listen, and pick up from what you said.

Controls

Built for overlap

The settings that make overlapping speech feel natural instead of chaotic.

  • Interruptions

    The agent stops when the caller cuts in, then decides what to do with what it heard. Sensitivity is set per agent.

  • No false stops

    A cough or a short “yes” should not end the agent’s sentence, so an interruption only counts after a minimum number of words.

  • Listening cues

    Short acknowledgements while the caller talks, so they know someone is there. Choose the words and how often.

    • Pre-synthesized at session start
    • No added delay
  • Turn detection

    Knowing when a turn really ends is what makes overlap safe.

    • 23 languages
    • ~12 ms inference
  • Room tone

    Optional background audio, such as a quiet office, so a pause never sounds like a dropped call.

  • Noise suppression

    Background noise is filtered before it can be mistaken for the caller talking.

Which engine fits?

Same tools, knowledge and phone numbers on all three. The engine is chosen per agent.

CascadingSTT → LLM → TTS
How it works
Speech-to-text, then a language model, then text-to-speech
Response feel
Fast, with every stage streaming
Control
Highest. Swap STT, model and voice independently
What you can inspect
Transcript, model and voice latency, end to end
Reach for it when
You need a specific voice, a specific model, or strict tool use
Speech-to-speechAudio in, audio out
How it works
One realtime model takes audio in and returns audio
Response feel
Fastest to first word; no transcription hop
Control
Choose the model and its voice; one provider per call
What you can inspect
Transcript and end-to-end latency
Reach for it when
Speed and natural tone matter more than per-stage control
Full duplexListens while it talks
How it works
Keeps listening while it speaks, so callers can overlap and interrupt
Response feel
Most like a person; overlaps, backchannels, barge-in
Control
Tune interruption sensitivity and listening cues
What you can inspect
Full transcript and call detail
Reach for it when
Callers talk over each other and the agent must keep up

Tell us what you are building

Tell us what you are making. We will walk you through the engines, the API, and what it takes to run it in production.