Edgewise API
    Preparing search index...

    Interface ClonedVoice

    The speaker conditioning Chatterbox computes from reference audio. Reusable across sentences and sessions.

    interface ClonedVoice {
        audio_features: SerializedTensor;
        audio_tokens: SerializedTensor;
        kind: "cloned-voice";
        model: string;
        speaker_embeddings: SerializedTensor;
        speaker_features: SerializedTensor;
    }
    Index
    audio_features audio_tokens kind model speaker_embeddings speaker_features
    audio_features: SerializedTensor
    audio_tokens: SerializedTensor
    kind: "cloned-voice"
    model: string
    speaker_embeddings: SerializedTensor
    speaker_features: SerializedTensor

    Settings
    Member Visibility

    On This Page
    Properties