Workflow
Make it in Riffusion, then take mp3 audio into Vocal Slice. Matched from what each app's own site says it takes in and gives out.
Step 1
Generate music from visual spectrograms using diffusion models.
Step 2
Takes mp3 audio from Riffusion. Cut audio recordings by selecting text from transcripts.
More about Riffusion · Ask Vibed Guide for a longer workflow