This is an event broadcasted by Tavus.
A conversation.utterance.streaming event is sent progressively as the replica speaks, containing the accumulated text spoken so far. The final event includes final: true and, if the replica was interrupted, is_interrupted: true.
Use content_index for network ordering. Use the speech field on the final event for an accurate transcript of what was actually spoken.
Documentation Index
Fetch the complete documentation index at: https://docs.tavus.io/llms.txt
Use this file to discover all available pages before exploring further.
Message type indicates what product this event will be used for. In this case, the message_type will be conversation
"conversation"
This is the type of event that is being sent back. This field will always be conversation.utterance.streaming.
"conversation.utterance.streaming"
A globally monotonic sequence number assigned to each event. Use this to determine the ordering of events — a higher seq means the event was sent later. This is useful for reconciling events that may arrive out of order.
42
The unique identifier for the conversation.
"c123456"
A unique identifier for the replica's current inference turn. Can be used to correlate with other events such as conversation.utterance and conversation.replica.started_speaking.
"83294d9f-8306-491b-a284-791f56c8383f"
The conversation turn index. This value increments each time a conversation.respond interaction is received, and groups all events that belong to the same conversational turn. Use this to correlate events (utterances, tool calls, speaking state changes, etc.) that are part of the same turn.
3
Contains the accumulated spoken text and metadata about the streaming state.