Transcriptisteğe bağlı
Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only.
Languageisteğe bağlı
Language for text alignment. Use the appropriate code for non-English synthesis.
Num Extra Stepsisteğe bağlı
Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence.
Temperatureisteğe bağlı
Sampling temperature for text token generation. Must be greater than 0. Higher values produce more varied output.
Top Pisteğe bağlı
Top-p (nucleus) sampling parameter for text generation.
Repetition Penaltyisteğe bağlı
Penalty applied to repeated tokens during generation.
Acoustic Cfg Scaleisteğe bağlı
Classifier-free guidance scale for acoustic feature generation.
Noise Temperatureisteğe bağlı
Temperature for noise in the flow matching diffusion process.
Num Inference Stepsisteğe bağlı
Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed.
Speed Up Factoristeğe bağlı
Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down.
Output Formatisteğe bağlı
The format of the output audio file.
Enable Safety Checkeristeğe bağlı
Authorized callers may set false to request relaxed screening.
