Meeting recaps
Turn meetings into decisions, action items, and readable summaries without forcing everyone to replay the recording.
MediaSFU AI Notes attaches to a live room, captures the transcript pipeline, and produces readable post-session artifacts. Use it for meeting recaps, support handoffs, multilingual sessions, and notes-only rooms where translated playback is not needed.
Start from a room or demo that already supports AI Notes. After the session, review notes in Dashboard or use public access if the host enabled sharing.
Try the demosUse Dashboard translation configs to save provider settings and AI note defaults, then attach the saved nickname when creating rooms.
Open DashboardEnable the translation runtime, provide a translation config nickname, and turn on enableAiNotes or aiNotesOnly at room creation.
Read setup docsTurn meetings into decisions, action items, and readable summaries without forcing everyone to replay the recording.
Give the next teammate a clean package after a call: transcript, summary, open questions, and follow-up context.
Run notes alongside translated rooms, or keep the room text-only when all you need is transcript and summary output.
Set STT and LLM provider choices on the translation config. Add TTS if the room also needs translated voice playback.
MediaSFU captures transcript entries during the room and keeps the note pipeline attached to that session.
After the session finalizes, notes and transcript files become available when generation and persistence are enabled.
Owners use Dashboard for review. Public viewers only see shared files through the passcode-protected AI Notes page.
Use an explicit language when you know it. Auto-detection is convenient for broad demos, but it is not the strongest benchmark for every language or dialect.
Speech models have different strengths by language, dialect, region, and acoustic conditions. Compare candidates such as Sarvam, AssemblyAI, and Speechmatics with the same source audio; these examples are not a universal ranking.
Evaluate with the microphones, accents, room noise, speaking pace, and vocabulary your production sessions will actually contain.
Treat speech recognition and note generation as separate layers. First verify the transcript, then tune the LLM prompt and summary structure.
For a production accuracy decision, configure the expected spoken language and compare providers using the same representative recording. No single STT provider is best for every language, dialect, accent, region, or recording environment.
AI Notes use the same real-time speech pipeline as translation. The room needs a usable translationConfigNickName, even when participants only need notes.
Use enableAiNotes for normal rooms, or aiNotesOnly when you want transcription and summaries without translated audio playback.
Keep notes private in the owner dashboard, or enable public access when outside viewers should retrieve safe exports with room name and passcode.
This is the common payload when you want transcripts and AI notes without translated playback for participants.
{
"supportTranslation": true,
"translationConfigNickName": "meeting-notes",
"translationOutputMode": "text-only",
"enableAiNotes": true,
"aiNotesOnly": true
}supportTranslation, translationConfigNickName, enableAiNotes, aiNotesOnly, and translationOutputMode decide what runs for a room.
aiNoteTakerConfig belongs on the translation config when you want reusable note behavior across rooms.
aiNotesOnly keeps the translation runtime available for transcript and summary generation, but normalizes output to text-only.
Public access is optional. When enabled, the safe retrieval page still requires the room name and passcode.
Markdown summary output for meeting recap, decisions, action items, and follow-up sections.
Readable markdown transcript for review, internal documentation, and handoff workflows.
Plain-text transcript for search, archiving, downstream processing, or custom workflows.
Signed-in owners get owner-scoped AI Notes history, previews, and export actions.
Open dashboardExternal viewers can load shared notes and transcripts only when they have the room name and passcode.
Open public accessSee the room flags, aiNoteTakerConfig fields, REST routes, and notes-only normalization rules.
Read docsConfirm the room used a valid translationConfigNickName and had enableAiNotes or aiNotesOnly enabled before the session started.
Download the transcript first, then check whether generateNotes and persistArtifacts are enabled on the note-taker configuration.
Public access must be enabled by the owner, and the viewer needs the exact room name plus passcode. Session ID is only needed for repeated rooms.
Inspect the transcript first. If recognition is weak, set the language explicitly, compare STT providers, and test representative audio. If the transcript is sound, tune transcript caps, chunk duration, the LLM credential, and the aiNoteTakerConfig prompt.
The reference covers REST routes, authenticated app configuration, aiNoteTakerConfig limits, notes-only normalization, and public sharing boundaries.