Skip to content

Add Real-Time Meeting Transcription and Notes Generator#96

Open
sazed-bot[bot] wants to merge 1 commit into
mainfrom
recipe/real-time-meeting-transcription-and-notes-generator-20260525
Open

Add Real-Time Meeting Transcription and Notes Generator#96
sazed-bot[bot] wants to merge 1 commit into
mainfrom
recipe/real-time-meeting-transcription-and-notes-generator-20260525

Conversation

@sazed-bot

@sazed-bot sazed-bot Bot commented May 25, 2026

Copy link
Copy Markdown
Contributor

Source URLs

Assessor score

  • Score: 5
  • Version: assessor_llm_v2

Synopsis

A LiveKit Agents template for a listen-only meeting notetaker: joins a WebRTC room, streams audio to AssemblyAI Universal-3 Pro STT with meeting-tuned turn detection (560ms min / 2000ms max silence, keyterms prompt), and on End Meeting sends the transcript to Cerebras Llama to produce structured notes (summary, key points, decisions, action items). Includes Next.js client, Python agent, prompt.md, and guide.mdx.

Reasoning

Clears all disqualifiers: public repo with concrete artifacts (D5/D6 pass), specific use case beyond hello-world (D1 pass), multi-component stack across orchestration/STT/LLM/telephony. Schema-able and forkable are maxed. Outcome loses a point because industry is horizontal/generic rather than a named vertical. Stack is clearly multi-component with real named products from the allow-list.

Claude raw output

{
  "id": "meeting-notes-assemblyai-livekit",
  "slug": "meeting-notes-assemblyai-livekit",
  "tags": [
    "meeting-notes",
    "transcription",
    "listen-only",
    "assemblyai",
    "cerebras"
  ],
  "title": "Real-Time Meeting Transcription and Notes Generator",
  "config": {
    "no_tts": true,
    "description": "Listen-only agent that never speaks, only transcribes",
    "passive_mode": true,
    "keyterms_prompt": "Meeting vocabulary",
    "max_turn_silence": 2000,
    "min_turn_silence": 560
  },
  "source": "github_discovery",
  "license": "Proprietary",
  "metrics": {
    "cost_display": null,
    "latency_p50_ms": null,
    "latency_p95_ms": null,
    "latency_display": null,
    "cost_per_minute_usd_max": null,
    "cost_per_minute_usd_min": null
  },
  "demo_url": null,
  "industry": "other",
  "pipeline": {
    "llm": "Cerebras Llama 3.3 70B",
    "stt": "AssemblyAI Universal-2",
    "tts": "Cartesia Sonic Turbo",
    "telephony": "Web Only"
  },
  "use_case": "transcription-and-summary",
  "framework": "LiveKit Agents",
  "languages": [
    "en-US"
  ],
  "created_at": "2025-05-15T10:30:00-07:00",
  "raw_prompt": null,
  "updated_at": "2025-05-15T10:30:00-07:00",
  "contributor": {
    "github": "seanflyyy"
  },
  "description": "A listen-only meeting agent that joins video calls, transcribes speech in real time using streaming STT, and generates structured meeting notes including summary, key points, decisions, and action items at the end of each session.",
  "prompt_file": null,
  "github_source_url": "https://github.com/sampleapp-ai/assemblyai-meeting-notes-livekit"
}

Dedup decision

F6 dedup has not landed yet; no dedup decision available.

Reviewer notes

approve-to-pr running:

@sazed-bot sazed-bot Bot added manual Added by speechstack-pipeline. recipe Added by speechstack-pipeline. score-5 Added by speechstack-pipeline. labels May 25, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

manual Added by speechstack-pipeline. recipe Added by speechstack-pipeline. score-5 Added by speechstack-pipeline.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants