PlayDiffusion

Upload an audio file and run ASR to get the text.

Then, specify the desired output text.

Run the inpainter to generate the modified audio.

Note: The model and demo are currently targeted for English.
1 100
0.5 10
0 10
0 10
0 1
1 10000

Audio Token Syllable Ratio

Automatic calculation (recommended) provides the best results in most cases.