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