Capability
Two ways to power a conversation — pick what fits.
Run the standard pipeline (speech-to-text, a language model, text-to-speech) or a single real-time audio-native model — both produce a real conversation, with different trade-offs.
What it actually does
Standard pipeline: separate speech recognition, language understanding, and voice, each independently configurable
Real-time option: one audio-native model handles the whole conversation directly
Switch per script — not a platform-wide, all-or-nothing choice
Both options support live interruption and human handoff the same way
The pipeline
One capability, end to end.
1
Call arrives
2
Pipeline or real-time model selected per script
3
Conversation happens
4
Response delivered
5
Handoff or booking happens the same either way