Add live captions to a LiveKit voice room

Publish an audio room as a captioned vertical video without building a speech pipeline or a headless browser farm.

Open in Playground Download Job JSON View demo code

The pipeline

LiveKit audio
ASR node
caption data events
web capture overlay
RTMP output

What this replaces

Build it yourself

Forward every participant track to a speech service
Align transcript events with speakers and timing
Render captions into a vertical canvas
Run and record a browser at production quality

With AVFlow

Let the ASR node produce text events
Send events to your LiveKit client or backend
Render captions in your own web page
Capture that page with web_capture and push it to RTMP

The validated Job

This is the same file 22-voice-room-captions.json serves. Replace platform credentials, output URLs, and storage secrets before running it.

22-voice-room-captions.json Download

{
  "name": "voiceroom-captions",
  "sources": [
    {
      "name": "room",
      "type": "livekit",
      "config": {
        "serverUrl": "wss://your-project.livekit.cloud",
        "token": "<subscribe-token>",
        "select": {
          "mediaTypes": [
            "audio"
          ],
          "excludeIdentities": [
            "avflow-captions"
          ]
        }
      }
    },
    {
      "name": "overlay",
      "type": "web_capture",
      "config": {
        "url": "https://your-app.example.com/overlay/captions?room=voice-room",
        "captureElement": "canvas#stage",
        "fps": 30,
        "captureAudio": false,
        "waitForSelector": {
          "selector": "canvas#stage[data-ready=\"true\"]",
          "timeout": 20000
        }
      }
    },
    {
      "name": "carrier",
      "type": "video_generator",
      "config": {
        "width": 16,
        "height": 16,
        "fps": 5,
        "backgroundColor": "#000000"
      }
    }
  ],
  "nodes": [
    {
      "name": "captions",
      "type": "asr",
      "inputs": [
        "room"
      ],
      "config": {
        "language": "multi"
      }
    },
    {
      "name": "floor",
      "type": "audio_mixer",
      "inputs": [
        "room"
      ],
      "config": {}
    }
  ],
  "sinks": [
    {
      "name": "to_room",
      "type": "livekit",
      "inputs": [
        "carrier",
        {
          "name": "captions",
          "select": {
            "mediaTypes": [
              "data"
            ]
          }
        }
      ],
      "config": {
        "serverUrl": "wss://your-project.livekit.cloud",
        "token": "<publish-token>",
        "videoTrackName": "avflow-caption-carrier"
      }
    },
    {
      "name": "live",
      "type": "rtmp_push",
      "inputs": [
        {
          "name": "overlay",
          "select": {
            "mediaTypes": [
              "video"
            ]
          }
        },
        "floor"
      ],
      "config": {
        "urls": [
          "rtmp://ingest.example.com/live/<stream-key>"
        ],
        "encoding": {
          "videoCodec": "h264",
          "audioCodec": "aac",
          "videoBitrateBps": 3500000,
          "audioBitrateBps": 128000,
          "keyframeIntervalSec": 2
        }
      }
    }
  ],
  "policies": {
    "maxDurationSec": 14400,
    "idleTimeoutSec": 120
  }
}

Submit it API

curl -X POST "https://api.avflow.dev/v1/jobs" \
  -H "Authorization: Bearer $AVFLOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d @22-voice-room-captions.json

Know the limits before you ship

You write the overlay page; AVFlow captures it rather than designing it for you.
The ASR node emits text events — summarization and display logic stay in your app.
A caption-capable streaming sink still needs a video input to carry subtitles.

Keep reading

ASR node Data events Web capture source

Run this LiveKit pipeline

Generate the Job in Playground, then run it with $20 promotional credit.

Open in Playground Open Console