Skip to main content

Build with fal

Complete documentation for the generative media platform powering the world’s top AI apps. Get 10x faster performance with ready-to-use models or deploy your own.

fal demo
Models API

600+ generative media models.
Ready for production.

Serverless

On-demand, serverless GPUs.
Scale to 1000s of H100s.

Compute

Dedicated clusters.
Built for heavy workloads.

Models API
Serverless
Compute
fal demo
Deploy Text-to-Speech Model
Deploy with Custom Containers
Build Custom Workflow UI
Generate Videos from Images
Deploy Multi-GPU Inference
Generate Images from Text
Convert Speech to Text
Use Large Language Models
Integrate with n8n
Deploy Text-to-Image Model
Deploy Text-to-Video Model
Deploy Text-to-Music Model
fal demo
Models API
Serverless
Compute