使い方
- インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
- 必要なツール、認証情報、対応環境を原文で確認します。
- 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill whisper-transcription開始前の確認
- 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
- スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文
見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。
Whisper Transcription
Transcribe any audio or video to text using OpenAI's Whisper model - the same technology powering ChatGPT voice features.
When to Use This Skill
- Podcast repurposing - Convert episodes to blog posts, show notes, social snippets
- Video subtitles - Generate SRT/VTT files for YouTube, social media
- Interview extraction - Pull quotes and insights from recorded calls
- Content audit - Make audio/video libraries searchable
- Translation - Transcribe and translate foreign language content
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Structures production workflow | Final creative direction |
| Suggests technical approaches | Equipment and tool choices |
| Creates templates and checklists | Quality standards |
| Identifies best practices | Brand/voice decisions |
| Generates script outlines | Final script approval |
Dependencies
bash
pip install openai-whisper torch ffmpeg-python click
# Also requires ffmpeg installed on system
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpegCommands
Transcribe Single File
bash
python scripts/main.py transcribe audio.mp3 --model medium --output transcript.txt
python scripts/main.py transcribe video.mp4 --format srt --output subtitles.srtBatch Transcription
bash
python scripts/main.py batch ./recordings/ --format txt --output ./transcripts/Transcribe + Translate
bash
python scripts/main.py translate foreign-audio.mp3 --to enExtract Timestamps
bash
python scripts/main.py timestamps podcast.mp3 --format jsonExamples
Example 1: Podcast to Blog Post
bash
# Transcribe 1-hour podcast
python scripts/main.py transcribe episode-42.mp3 --model medium
# Output: episode-42.txt (full transcript with timestamps)
# Processing time: ~5 min for 1 hour audio on M1 MacExample 2: YouTube Subtitles
bash
# Generate SRT for video upload
python scripts/main.py transcribe marketing-video.mp4 --format srt
# Output: marketing-video.srt
# Upload directly to YouTube/VimeoExample 3: Batch Process Interview Library
bash
# Transcribe all recordings in folder
python scripts/main.py batch ./customer-interviews/ --model small --format txt
# Output: ./customer-interviews/*.txt (one per audio file)Model Selection Guide
| Model | Speed | Accuracy | VRAM | Best For |
|---|---|---|---|---|
tiny | Fastest | ~70% | 1GB | Quick drafts, short clips |
base | Fast | ~80% | 1GB | Social media clips |
small | Medium | ~85% | 2GB | Podcasts, interviews |
medium | Slow | ~90% | 5GB | Professional transcripts |
large | Slowest | ~95% | 10GB | Critical accuracy needs |
Recommendation: Start with small for most marketing content. Use medium for client deliverables.
Output Formats
| Format | Extension | Use Case |
|---|---|---|
txt | .txt | Blog posts, analysis |
srt | .srt | Video subtitles (YouTube) |
vtt | .vtt | Web video subtitles |
json | .json | Programmatic access |
tsv | .tsv | Spreadsheet analysis |
Performance Tips
- GPU acceleration - 10x faster with CUDA GPU
- Audio extraction - Script auto-extracts audio from video
- Chunking - Long files auto-split for memory efficiency
- Language detection - Automatic, or specify with
--language
Skill Boundaries
What This Skill Does Well
- Structuring audio production workflows
- Providing technical guidance
- Creating quality checklists
- Suggesting creative approaches
What This Skill Cannot Do
- Replace audio engineering expertise
- Make subjective creative decisions
- Access or edit audio files directly
- Guarantee commercial success
Related Skills
- video-processing - Extract audio from video
- youtube-downloader - Download videos to transcribe
- content-repurposer - Transform transcripts to content
- podcast-production - Create podcasts
Skill Metadata
- Mode: cyborg
yaml
category: automation
subcategory: audio-processing
dependencies: [openai-whisper, torch, ffmpeg-python]
difficulty: beginner
time_saved: 10+ hours/week
