Durationisteğe bağlı
Upper bound on the generated audio length in seconds. The model may stop earlier; the actual duration is returned in the output.
Seedisteğe bağlı
Random seed for reproducibility. If not provided, a random seed will be used.
Num Inference Stepsisteğe bağlı
Number of flow-matching Euler steps per 8-second denoising chunk. More steps improve quality at the cost of speed.
Guidance Scaleisteğe bağlı
Classifier-free guidance scale of the flow-matching stage.
Enable Safety Checkeristeğe bağlı
Authorized callers may set false to request relaxed screening.
