Mixed and per-participant media
| Mixed | Per-participant | |
|---|---|---|
| Source | A PBX conference, dialled in over SIP | A LiveKit room through the WebRTC worker |
| What the engine receives | One stream carrying everyone | One tagged stream per participant, plus sampled camera frames |
| Transcript speakers | unknown, unless the provider labels them | Per participant, from that participant’s own track |
| Per-participant analysis | Not possible | Yes: the flow analyses each segment it is handed (call-segment), for analysed roles only |
| Recording | One recording of the mix | One recording per participant, audio only |
A conference dial-in is one mixed channel, so a live transcription cannot say who spoke. Providers
such as OpenAI Realtime and Gemini Live label no speakers, so the transcript marks the speaker as
unknown with the source none; attribute speakers afterwards, for example with a model over the
transcript, and say that they were inferred.
Per-participant media is where emotion and engagement analysis, if you use it, is possible at all, and also where the compliance obligations bite hardest. See Emotion analytics and compliance.
Sutra Voice does not mix: a mixed stream is whatever the PBX produced. Hosted per-participant audio on PBXs is on the Roadmap.