Transcript isteğe bağlı
Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only.
Language isteğe bağlı
Language for text alignment. Use the appropriate code for non-English synthesis.
En Ar Ch De Es Fr It Ja Pl Pt
Num Extra Steps isteğe bağlı
Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence.
Temperature isteğe bağlı
Sampling temperature for text token generation. Must be greater than 0. Higher values produce more varied output.
Top P isteğe bağlı
Top-p (nucleus) sampling parameter for text generation.
0 1
Repetition Penalty isteğe bağlı
Penalty applied to repeated tokens during generation.
1 2
Acoustic Cfg Scale isteğe bağlı
Classifier-free guidance scale for acoustic feature generation.
Noise Temperature isteğe bağlı
Temperature for noise in the flow matching diffusion process.
0 1 2
Num Inference Steps isteğe bağlı
Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed.
Speed Up Factor isteğe bağlı
Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down.
0.5 1.5
Output Format isteğe bağlı
The format of the output audio file.
Wav Mp3
Enable Safety Checker isteğe bağlı
Authorized callers may set false to request relaxed screening.
Açık Enable Safety Checker 