Real-time meeting data, over WebSockets
Don't wait for the meeting to end: stream raw audio or live speaker-attributed transcripts out of Zoom, Google Meet and Microsoft Teams calls as they happen — and stream audio back in for interactive agents.
One config block, two modes
Set streaming_config on the bot: mode "audio" delivers raw meeting audio to your WebSocket at 16, 24, 32 or 48 kHz; mode "transcription" delivers live speech-to-text. Provide an input_url and the bot plays your audio into the meeting.
curl -X POST "https://api.meetingbaas.com/v2/bots" \
-H "Content-Type: application/json" \
-H "x-meeting-baas-api-key: $API_KEY" \
-d '{
"meeting_url": "https://meet.google.com/abc-def-ghi",
"bot_name": "Live Bot",
"streaming_config": {
"mode": "transcription",
"output_url": "wss://your-app.example.com/meeting-stream",
"audio_frequency": 24000
}
}'Live audio out
Raw meeting audio pushed to your WebSocket in real time — feed voice agents, compliance monitors or live translation pipelines at 16 to 48 kHz.
Live transcripts
Real-time speech-to-text as the meeting happens, including an ElevenLabs option for streaming transcription — build live captions, agent context or in-meeting copilots.
Audio in
Stream audio into the meeting through the bot — the foundation for speaking agents that answer questions or give updates live.
Recording still included
Streaming runs alongside the standard pipeline: you still get the full recording, transcript and metadata by webhook after the call, at the same flat token rates.
Streaming adds 0.10 tokens per hour per direction on top of the 1 token per hour recording rate. Model your usage on the pricing calculator.
Real-time streaming FAQ
Ready to ship meeting bots without building the plumbing?
Join thousands of customers that use Meeting BaaS to create AI Meeting Assistants, customer interactions analytics, and much more. Start your journey today.