Real-time media cloud

One platform for
every live media workflow

AVFlow connects LiveKit, Daily, Jitsi, Agora, RTMP, and more to layouts, AI nodes, and outputs you choose. Describe a Job in JSON, submit it once, and run countless combinations — from stream relays to AI-powered shows.

LiveKitDailyJitsiAgoraRTMPSRTWHIPS3
9+
Source types
5
Processing nodes
9+
Output sinks
REST
Job API

Why AVFlow

Compose what you need from proven building blocks

Pick inputs, processing, and destinations independently. The same Job model covers a simple relay or a multi-output mix with captions and AI.

Familiar integrations

Connect the RTC platforms and streaming protocols you already use — no custom ingest SDK required.

Mix & match freely

Combine sources, layout nodes, AI nodes, and outputs in one Job. Grid shows, speaker layouts, and multi-bitrate ladders all use the same model.

AI-native nodes

Add real-time captions with ASR, speech-to-speech with voice_agent, or digital humans with avatar — then route results to rooms, CDNs, or storage.

Parallel outputs

Push to YouTube and Twitch, record to S3, and publish back into a room — up to three sinks from one Job.

Browser compositing

Capture slides, scoreboards, or lower-thirds from a web page and blend them into the live mix.

API-first control

Submit, list, inspect, and stop Jobs with a single REST API. Webhooks notify your app when state changes.

Use cases

From mix to AI applications

01

Room → CDN mix

Composite a LiveKit, Daily, Jitsi, or Agora room and push to any RTMP endpoint with layout control.

02

Cloud recording

Composite grid or speaker layouts recorded to HLS on S3.

03

Live captions

ASR into WebVTT recordings, FLV side-channels, or real-time data messages in the room.

04

AI voice & avatar

Build voice agents and digital-human experiences that hear the room and respond on stream.

Ready to ship your first job?

Copy an example, POST to the API, and go live in minutes.