Available Models

This page lists the top models for each task. Pass the Endpoint ID to any client library or to https://queue.fal.run/<endpoint-id>. Input → Output lists the media types that an endpoint accepts and returns. Under each model, API links to the endpoint’s schema and code examples, and Model page links to its playground on fal.ai. Most models have more than one endpoint, for example text-to-video and image-to-video. The model page lists all of them.

​

Generate Video

Create video from a text prompt, a starting image, or audio.

​

Edit and Transform Video

Edit, restyle, dub, upscale, extend, or otherwise transform an existing video.

​

Generate Images

Create images from a text prompt.

​

Edit and Transform Images

Edit, restyle, upscale, segment, or otherwise transform existing images.

​

Generate Audio

Create speech, music, and sound effects.

​

Process Audio

Transcribe speech, convert voices, and transform audio.

​

Vision

Caption, describe, detect, and answer questions about images and video.

​

Generate 3D

Create and process 3D assets from text, images, or meshes.