Audio to Audio — Stable Audio 3 Medium audio inpainting is a 1.4 billion parameter latent diffusion model that fills in or reworks selected segments of a stereo track guided by text prompts, supporting single- and multi-segment editing.

≈ 39.613 kredi/üretim

Ayarlar

Audio Urlzorunlu

Source audio. Only the masked region is regenerated.

Mask Start Secondszorunlu

Start of the region to regenerate, in seconds.

Mask End Secondszorunlu

End of the region to regenerate, in seconds.

Negative Promptisteğe bağlı

Text description of qualities to avoid in the output.

Num Inference Stepsisteğe bağlı

Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.

Guidance Scaleisteğe bağlı

Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.

Seedisteğe bağlı

Random seed for reproducible outputs. Omit for a random seed.

Enable Prompt Expansionisteğe bağlı

If True, the prompt will be expanded using an LLM for more detailed and higher quality results.

Enable Safety Checkeristeğe bağlı

Enable NSFW content safety checking.

Output Formatisteğe bağlı

Container format for the generated audio output.

Bitrateisteğe bağlı

Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap