TopRank Skills

Home / Claw Skills / Git / GitHub / youtube-transcriber
Official OpenClaw rules 36%

youtube-transcriber

One-command YouTube video transcription. Automatically downloads audio and transcribes using OpenAI Whisper API — works even when YouTube subtitles are disabled. Use when asked to "transcribe this video", "get transcript", "what does this video say", or when YouTube captions are unavailable.

Stars

0

Installs

0

Status

ACTIVE

Visibility

PUBLIC

安装方式

直接复制以下提示词,发送给你的 AI 助手即可完成安装。

请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 youtube-transcriber 技能。 若已安装,则直接安装 youtube-transcriber 技能。

Overview

Skill Key
edisonchenai/youtube-transcriber
Author
edisonchenai
Source Repo
openclaw/skills
Version
-
Source Path
skills/edisonchenai/youtube-transcriber
Latest Commit SHA
0fb0a7b8db3f36f4179fb9b1dbaaa6417246af31

Extracted Content

SKILL.md excerpt

# YouTube Transcriber

One-command transcription for any YouTube video — even when subtitles are disabled.

**How it works:**
1. Tries to fetch existing YouTube subtitles first (free, instant)
2. If subtitles are disabled/unavailable → downloads audio → transcribes via OpenAI Whisper API

## Prerequisites

- `yt-dlp` — `brew install yt-dlp` or `pip install yt-dlp`
- `ffmpeg` — `brew install ffmpeg`
- `OPENAI_API_KEY` environment variable set

## Usage

```bash
# Basic — auto-detect best method
{baseDir}/scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID"

# Specify language (improves accuracy for non-English)
{baseDir}/scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --lang zh

# Custom output path
{baseDir}/scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --out /tmp/transcript.txt

# Force Whisper (skip subtitle check)
{baseDir}/scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --force-whisper

# Keep downloaded audio file
{baseDir}/scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --keep-audio
```

## Options

| Option | Description | Default |
|--------|-------------|---------|
| `--lang <code>` | Language hint (ISO 639-1: en, zh, ja, ko, etc.) | auto-detect |
| `--out <path>` | Output transcript file path | `/tmp/yt_transcript_<VIDEO_ID>.txt` |
| `--force-whisper` | Skip subtitle check, always use Whisper API | off |
| `--keep-audio` | Keep the downloaded audio file after transcription | off (deletes audio) |
| `--audio-bitrate <kbps>` | Audio compression bitrate | 64 |

## How It Works

```
YouTube URL
    │
    ├─► Try yt-dlp subtitles (free, instant)
    │       │
    │       ├─ Found → Clean & output transcript ✓
    │       │
    │       └─ Not found / disabled
    │               │
    │               ▼
    └─► Download audio (yt-dlp + ffmpeg)
            │
            ├─ Compress to mono, low bitrate (fit 25MB API limit)
            │
            ▼
        OpenAI Whisper API → tran...

README excerpt

# YouTube Transcriber

One-command YouTube video transcription for [Claude Code](https://claude.com/claude-code). Works even when YouTube subtitles are disabled.

## How It Works

1. **Fast path**: Tries to fetch existing YouTube subtitles (free, instant)
2. **Fallback**: Downloads audio → compresses → transcribes via OpenAI Whisper API

```
YouTube URL → [subtitles available?] → YES → clean transcript ✓
                                     → NO  → download audio → Whisper API → transcript ✓
```

## Install

```bash
npx clawhub install youtube-transcriber
```

Or install directly from GitHub:

```bash
# Clone to your Claude Code skills directory
git clone https://github.com/EdisonChenAI/youtube-transcriber.git ~/.claude/skills/youtube-transcriber
```

## Prerequisites

- **yt-dlp**: `brew install yt-dlp` or `pip install yt-dlp`
- **ffmpeg**: `brew install ffmpeg`
- **OPENAI_API_KEY**: Required only when subtitles are unavailable

## Usage

```bash
# Basic usage
./scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID"

# Chinese video
./scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --lang zh

# Custom output path
./scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --out ./transcript.txt

# Force Whisper API (skip subtitle check)
./scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --force-whisper

# Keep the downloaded audio file
./scripts/transcribe.sh "https://www.youtube.com/watch?v=VIDEO_ID" --keep-audio
```

## Options

| Option | Description | Default |
|--------|-------------|---------|
| `--lang <code>` | Language hint (en, zh, ja, ko, etc.) | auto-detect |
| `--out <path>` | Output transcript file path | `/tmp/yt_transcript_<ID>.txt` |
| `--force-whisper` | Always use Whisper API | off |
| `--keep-audio` | Keep downloaded audio | off |
| `--audio-bitrate <kbps>` | Compression bitrate | 64 |

## Cost

| Method | Cost | Speed |
|--------|------|-------|
| Subtitles available | Free | Instant |
| Whisper...

Related Claw Skills

heyixuan2

bambu-studio-ai

★ 41

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D).

capt-marbles

geo-optimization

★ 1

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.

carlulsoe

parakeet-stt

★ 0

Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, or processing voice recordings locally without cloud APIs.

carlzhao007

feishu-process-feedback

★ 0

飞书消息自动处理与进度反馈技能。安装后后台运行,监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈(任务确认、进度百分比、完成通知)。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化。 使用场景:飞书自动化工作流、任务进度追踪、批量任务处理、需要实时反馈的场景。

cartoonitunes

bottyfans

★ 0

BottyFans agent skill for autonomous creator monetization. Lets AI agents register, build a profile, publish posts (public, subscriber-only, or pay-to-unlock), upload media, accept USDC subscriptions and tips on Base, send and receive DMs, track earnings, and appear on the creator leaderboard. Use this skill when an agent needs to monetize content, interact with fans, manage a creator profile, handle payments in USDC, or operate as an autonomous creator on the BottyFans platform.

camopel

arxivkb

★ 0

Local arXiv paper manager with semantic search. Crawls arXiv categories, downloads PDFs, chunks content, and indexes with FAISS + Ollama embeddings. No cloud API keys required — everything runs locally.