Conference Transcribe

Transcribe a multi-talk conference livestream or long YouTube video into separate per-talk transcripts. Parses timestamps from the video description to split talks, downloads audio/video, transcribes each segment, then uses an LLM to clean up and format the transcripts with key takeaways and frequent timestamps. Use when user says "transcribe this conference", "split this livestream into talks", "transcribe each talk separately", or provides a YouTube URL of a multi-hour event stream with chapter timestamps.

201 stars 12 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add swyxio/skills --skill conference-transcribe
Manual install
git clone --depth 1 https://github.com/swyxio/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/conference-transcribe ~/.claude/skills/conference-transcribe

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Conference Transcribe

Input: a YouTube URL with chapter timestamps or another multi-talk recording.

Transcribe a multi-talk conference livestream into individual, cleaned-up per-talk markdown files with key takeaways and frequent timestamps.

## Lessons Learned (from AIE Europe Day 1, April 2026)

This skill was born from a real transcription session. Here's what worked and what didn't:

### What Worked

1. **YouTube auto-captions as primary source** -- YouTube's English auto-captions (VTT) are surprisingly good and *instant*. No download wait, no model download, no GPU needed. Prefer this over Whisper for YouTube videos that have captions available.
2. **`yt-dlp --write-sub --write-auto-sub --sub-lang en`** to grab captions directly, then parse the VTT file.
3. **`yt-dlp --download-sections`** to download individual talk clips as MP4 (for archiving/sharing), parallelized with `ThreadPoolExecutor(max_workers=2)`.
4. **Parsing the video description** for chapter timestamps -- the description is the ground truth for talk boundaries.
5. **Two-pass transcript pipeline**: raw VTT parse -> LLM cleanup. The raw parse handles deduplication and timestamp bucketing; the LLM handles readability, proper nouns, key takeaways, and formatting.
6. **Opus compression** for cloud API uploads: `ffmpeg -c:a libopus -b:a 32k` gets 1 hour of audio down to ~14MB (under Groq/OpenAI's 25MB limit).
Read the full skill on GitHub

Details

Skill name
conference-transcribe
Repository
swyxio/skills
Path
conference-transcribe/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Conference Transcribe skill do?

Transcribe a multi-talk conference livestream or long YouTube video into separate per-talk transcripts. Parses timestamps from the video description to split talks, downloads audio/video, transcribes each segment, then uses an LLM to clean up and format the transcripts with key takeaways and frequent timestamps. Use when user says "transcribe this conference", "split this livestream into talks", "transcribe each talk separately", or provides a YouTube URL of a multi-hour event stream with chapter timestamps.

How do I install the Conference Transcribe skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add swyxio/skills --skill conference-transcribe. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Conference Transcribe popular?

It lives in swyxio/skills, which has 201 GitHub stars and 12 forks.

Related skills

Accelevents API

201

swyxio/skills

Use when reading or updating AI Engineer Europe speaker records through the Accelevents REST API, especially for full-record PUT updates, auth header quirks, and preserving existing speaker fields.

Software Development12

Accelevents Speaker Sync

201

swyxio/skills

Use when website speaker, session, schedule, room, track, or headshot changes must be synchronized back to Accelevents for AI Engineer Europe 2026.

AI, LLMs & Agents12

Agents SDK

201

swyxio/skills

Build or debug stateful applications that specifically use Cloudflare's `agents` package, including Agent classes, routing, callable methods, synchronized state, scheduling, AIChatAgent, durable execution, or Agents SDK client hooks. Do not trigger for generic AI-agent design, the OpenAI Agents SDK, or ordinary Durable Object work that does not use the Cloudflare Agents SDK.

AI, LLMs & Agents12

Conlang

191

jwynia/agent-skills

Generate phonologically consistent constructed languages for fiction. Use when you need naming languages, alien speech, or fantasy tongues without deep linguistics knowledge.

Images, Video & Audio24

Audiobook Production

150

guia-matthieu/clawfu-skills

Master ACX-compliant audiobook production using Audible's technical standards and Richard Mayer's multimedia learning principles for engaging, professional audio. Use when: Producing an audiobook for Audible/ACX distribution; Creating audio versions of courses or written content; Setting up narration workflow for long-form content; Ensuring audio meets professional distribution standards; Self-producing an audiobook as an author

Images, Video & AudioIn 1 list32

Design Apps with Imagegen

201

swyxio/skills

Explore and implement image-led app or site design changes, from a single element to a full screen, with varied visual directions, targeted inspiration, and user feedback. Use for design exploration, not routine UI fixes or implementation of an already selected design.

Images, Video & Audio12

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.