Stability Ai Stable Audio 3 Audio Inpainting

audio-to-audioRp. 885

Stability-Ai Stable-Audio-3 Audio-Inpainting

Stable Audio 3 Audio Inpainting regenerates a selected region of an audio clip from a prompt.

Field

Wajib

Masukkan instruksi utama yang akan diproses model.

Promptwajibstring

Text prompt describing the replacement audio for the masked region.

Negative Promptstring

Optional terms to avoid in the generated audio.

Unggah file langsung di field yang disediakan

Audiowajibstring

Source audio to edit.

Unggah audio

Drag & drop atau klik. Maks 25.0 MB.

audio

Pilih file dari perangkat

Atur Mask Start Seconds, Mask End Seconds, Num Inference Steps, Guidance Scale, dan parameter lain sesuai schema model.

Mask Start Secondsnumber

0 - 380

Start time of the region to inpaint, in seconds.

Mask End Secondsnumber

0 - 380

End time of the region to inpaint, in seconds. Must be greater than mask_start_seconds.

Num Inference Stepsinteger

1 - 100

Number of inference steps.

Guidance Scalenumber

0 - 25

Prompt guidance strength.

Output Formatstring

Output audio format.

Ringkasan

Hitung harga pasti sebelum membuat transaksi untuk mengetahui biaya yang dibutuhkan.

Model

Rp. 885

Stability-Ai Stable-Audio-3 Audio-Inpainting

Belum ada estimasi harga

Isi input, lalu hitung harga sebelum membuat payment.