fal

fal Realtime API

WebSocket-based realtime inference for ultra-low latency interactive generative experiences such as LCM/SDXL sketch-to-image, live-portrait, and realtime upscaling. Bi-directional binary/JSON messaging keeps a persistent connection open so each frame, prompt, or pose adjustment is processed in milliseconds. Powers fal.realtime client utilities used in canvas apps, drawing tools, AR experiences, and live video pipelines.

fal Realtime API is one of 9 APIs that fal publishes on the APIs.io network.

Tagged areas include AI, Generative AI, Realtime, WebSocket, and Streaming. The published artifact set on APIs.io includes API documentation and code examples.

GitHub

Documentation

📖
Documentation
https://fal.ai/docs/model-apis/real-time

Code Examples

💻
CodeExamples
https://github.com/fal-ai/real-time-demo-app

API entry from apis.yml

apis.yml Raw ↑ 
aid: fal-ai:fal-realtime-api
name: fal Realtime API
tags:
- AI
- Generative AI
- Realtime
- WebSocket
- Streaming
- Inference
humanURL: https://fal.ai/docs/model-apis/real-time
baseURL: wss://realtime.fal.run
properties:
- url: https://fal.ai/docs/model-apis/real-time
  type: Documentation
- url: https://github.com/fal-ai/real-time-demo-app
  type: CodeExamples
description: WebSocket-based realtime inference for ultra-low latency interactive generative experiences
  such as LCM/SDXL sketch-to-image, live-portrait, and realtime upscaling. Bi-directional binary/JSON
  messaging keeps a persistent connection open so each frame, prompt, or pose adjustment is processed
  in milliseconds. Powers fal.realtime client utilities used in canvas apps, drawing tools, AR experiences,
  and live video pipelines.