Overview
Generate photorealistic humans from audio inputs using Audio2Photoreal, a PyTorch implementation of the paper 'From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations' by Facebook Research.
Face Diffusion Model
Generates photorealistic faces from audio inputs using a face diffusion model.
Body Diffusion Model
Generates photorealistic bodies from audio inputs using a body diffusion model.
Body VQ VAE
Generates photorealistic bodies from audio inputs using a body VQ VAE model.
Body Guide Transformer
Generates photorealistic bodies from audio inputs using a body guide transformer model.
Get started
- Open the official website and confirm the service is available in your region.
- Check the current plan, usage limits and terms for your intended use.
- Try a small task with sample data before committing to a paid plan.
Editorial note
Pricing checked: Sep 20, 2026. Tiered plans available. Review current pricing and subscription options on the official website.
Record updated: Sep 20, 2026
Suggest a correction
