Utterance Event

{
  "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": "replica",
    "speech": "Full assistant reply for this inference.",
    "user_audio_analysis": "optional short summary",
    "user_visual_analysis": "optional short summary",
    "interrupted": true
  }
}

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 replica text and interruption flags.

message_type

string

conversation for conversation-layer app messages.

Example:

"conversation"

event_type

string

conversation.utterance.

Example:

"conversation.utterance"

timestamp

number

Unix timestamp (seconds since epoch) indicating when this event was created. Use this to build timestamped transcripts or reconstruct the timeline of a conversation.

Example:

1746000000.123

seq

integer

Monotonic per event; a higher seq was emitted later. Use with turn_idx as in Event ordering and turn tracking.

Example:

42

conversation_id

string

The unique identifier for the conversation.

Example:

"c123456"

inference_id

string

This is a unique identifier for a given utterance. In this case, it will be the utterance the replica is speaking.

Example:

"83294d9f-8306-491b-a284-791f56c8383f"

turn_idx

integer

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

properties

object

Omitted when empty. When the speaker is the user and the persona uses Raven-1, optional user_audio_analysis / user_visual_analysis may appear when non-empty.

Show child attributes

Append Conversational Context Interaction Utterance Streaming Event

⌘I

Documentation Index

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).