@langwatch/scenario
    Preparing search index...

    Interface UserSimulatorVoiceConfig

    Configuration for the voice path of the user simulator (§4.2).

    When voice is set, the simulator runs TTS on each generated text turn and emits an AudioMessageParam instead of a plain text message.

    interface UserSimulatorVoiceConfig {
        audioEffects?: ((audio: Uint8Array) => Uint8Array)[];
        interruptProbability?: number;
        persona?: string;
        voice?: string;
    }

    Hierarchy (View Summary)

    Index

    Properties

    audioEffects? interruptProbability? persona? voice?

    Properties

    audioEffects?: ((audio: Uint8Array) => Uint8Array)[]

    Optional array of audio effect functions applied to each synthesized audio turn AFTER the TTS cache hit (effects are never baked into the cache key). Each function receives the raw PCM16 bytes and returns transformed bytes.

    interruptProbability?: number

    Probability in [0, 1] that the simulator interrupts each agent turn during proceed() (PRD §4.2 interrupt_probability=0.3). The executor reads this inside the proceed loop and fires a barge-in per the configured chance. Unset/0 = never interrupt.

    persona?: string

    Optional persona description appended to the system prompt. Shapes the text content of the simulated user.

    voice?: string

    TTS voice identifier in provider/voice_name format, e.g. "openai/nova". When present, each simulator turn is synthesized to audio via this voice.

    Settings

    Member Visibility

    On This Page

    Properties