{
"message_type": "conversation",
"event_type": "conversation.utterance",
"seq": 600,
"conversation_id": "your-conversation-id",
"inference_id": "550e8400-e29b-41d4-a716-446655440000",
"turn_idx": 8,
"properties": {
"role": "pal",
"speech": "Full assistant reply for this inference.",
"participant_id": "p22f53b7b4b9",
"participant_name": "Charlie",
"user_audio_analysis": "optional short summary",
"user_visual_analysis": "optional short summary",
"interrupted": true
}
}Interaction Events
Utterance Event
Outbound: Tavus tells you who spoke and the full utterance text for that turn (from when they started until they finished, which may be more than one sentence).
Compare with conversation.utterance.streaming for progressive PAL text and interruption flags.
For PAL turns, Tavus sends duplicate app-messages with the same payload except properties.role: "pal" (use in new integrations) and "replica" (legacy). User turns use "user" only.
participant_id and participant_name say who spoke the turn, using the handle conversation.joined announced them under.
Monotonic per event; a higher seq was emitted later. Use with turn_idx as in Event ordering and turn tracking.
Example:
42
Turn index; increments when conversation.respond is processed. Groups utterances, tool calls, and speaking-state events for the same turn. See Event ordering and turn tracking.
Example:
3

