Add Real-Time Meeting Transcription and Notes Generator#96
Open
sazed-bot[bot] wants to merge 1 commit into
Open
Add Real-Time Meeting Transcription and Notes Generator#96sazed-bot[bot] wants to merge 1 commit into
sazed-bot[bot] wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Source URLs
Assessor score
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: