Class RunConfig

Speech configuration for the live agent

The output modalities. If not set, it's default to AUDIO.

Whether or not to save the input blobs as artifacts.

Whether to support CFC (Compositional Function Calling). Only applicable for StreamingMode.SSE. If it's true. the LIVE API will be invoked. Since only LIVE API supports CFC

Streaming mode, None or StreamingMode.SSE or StreamingMode.BIDI.

Output transcription for live agents with audio response.

Input transcription for live agents with audio input from user.

Realtime input config for live agents with audio input from user.

If enabled, the model will detect emotions and adapt its responses accordingly.

Configures the proactivity of the model. This allows the model to respond proactively to the input and to ignore irrelevant input.

A limit on the total number of llm calls for a given run.

Valid Values:

• More than 0 and less than Number.MAX_SAFE_INTEGER: The bound on the number of llm calls is enforced, if the value is set in this range.
• Less than or equal to 0: This allows for unbounded number of llm calls.