MeetStream Documentation

Deepgram Streaming pushes live transcript chunks to your webhook during the meeting. Three delivery modes: raw (default, Deepgram’s stream as it arrives), word_level (word by word) and sentence (punctuated sentences).

Enable

Streaming needs both the provider config and a live webhook URL:

{
  "meeting_link": "https://meet.google.com/abc-defg-hij",
  "bot_name": "Notetaker",
  "live_transcription_required": { "webhook_url": "https://your-server.com/live" },
  "recording_config": {
    "transcript": {
      "provider": { "deepgram_streaming": { "transcription_mode": "sentence" } }
    }
  }
}

CLI: meetstream bot create <link> -t deepgram_streaming --live-transcript-webhook <url>.

Configuration reference

Field	Type	Default	Notes
`model`	string	`nova-3` on Zoom and Teams, `nova-2` on Google Meet	Set it explicitly (for example `nova-3`) to use the same model on every platform
`transcription_mode`	string	`raw`	`raw`, `word_level` or `sentence`
`language`	string	`en`
`punctuate`	boolean	`true`
`smart_format`	boolean	`true`
`endpointing`	integer	`300`	Silence (ms) that ends a segment
`vad_events`	boolean	`true`	Voice-activity events
`utterance_end_ms`	integer	`1000`
`encoding`	string	`linear16`	Only supported value
`channels`	integer	`1`

The live payload

Each webhook delivery carries bot_id, speakerName, timestamp, new_text (the increment), transcript (running buffer), words[] with per-word timing and confidence, end_of_turn, and your echoed custom_attributes, full shape in Live Transcription.

Streaming providers deliver text during the call and create no post-call transcript, so MeetStream does not send transcription.processed. MeetStream sends bot.done when the session ends. Need both? Re-transcribe the recording after the call.