oezi13/PlayDiffusion-nonverbal
This is a finetune of PlayHT/PlayDiffusion for non-verbal tag support (<pause>, <laugh> and <breath>).
PlayDiffusion is a diffusion model which can 'inpaint' audio. So you can change existing audio (slightly) by providing new text.
For more information on usage visit https://github.com/coezbek/PlayDiffusion
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for oezi13/PlayDiffusion-nonverbal
Base model
PlayHT/PlayDiffusion