メニュー
Convert audio files (M4A, WAV, MP3) to Markdown transcripts. USE WHEN transcribe, audio to text, meeting recording, voice memo.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/phuaky/pai-skills --skill transcribeコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see AnalyticsTracking. USE WHEN ab test, split test, experiment setup, A/B test, multivariate.
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see AbTestSetup. USE WHEN analytics, tracking, GA4, measurement, Google Analytics.
Structure raw ideas into articulate outlines using Dan Koe's frameworks. USE WHEN articulate, structure ideas, outline talk, outline article, think through piece, brainstorm structure, how should I say this, organize my thoughts, structure this post, help me outline.
SKILL.md を表示中
| name | Transcribe |
| description | Convert audio files (M4A, WAV, MP3) to Markdown transcripts. USE WHEN transcribe, audio to text, meeting recording, voice memo. |
Convert audio files to clean Markdown transcripts. Auto-selects best backend.
/transcribe <audio-file>
/transcribe <audio-file> --azure # Force Azure gpt-4o-mini-transcribe (best quality)
/transcribe <audio-file> --groq # Force Groq whisper-large-v3-turbo (fastest)
/transcribe <audio-file> --local # Force local whisper.cpp (free)
AZURE_OPENAI_KEY + AZURE_OPENAI_ENDPOINT set (gpt-4o-mini-transcribe, lowest WER)GROQ_API_KEY set (216x realtime, cheapest API)When invoked, run:
~/.claude/skills/Transcribe/Tools/Transcribe.sh "<audio-file>" [--groq|--azure|--local]
Output saved to same directory as source: {name}-transcript.md
| Component | Path / Config |
|---|---|
| Transcribe.sh | ~/.claude/skills/Transcribe/Tools/Transcribe.sh |
| Azure API | AZURE_OPENAI_KEY, AZURE_OPENAI_ENDPOINT, deployment: gpt-4o-mini-transcribe (default) with whisper fallback |
| Groq API | GROQ_API_KEY env var, model: whisper-large-v3-turbo |
| whisper-cli | ~/tools/whisper.cpp/build/bin/whisper-cli |
| large-v3 model | ~/tools/whisper.cpp/models/ggml-large-v3.bin |
| Method | Cost | Speed | Quality | Best For |
|---|---|---|---|---|
| Azure (gpt-4o-mini-transcribe) | ~$0.30/hr | Fast | Best (lowest WER) | Default — best quality |
| Groq (turbo) | $0.04/hr | 216x realtime | Good | Bulk/fast transcription |
| Azure (whisper) | ~$0.36/hr | Fast | Good | Fallback |
| Local (large-v3) | FREE | ~1x realtime | Good | Offline, full privacy |
| Local (small.en) | FREE | ~3x faster | OK | Quick English drafts |
Set AZURE_TRANSCRIBE_DEPLOYMENT env var to use a different Azure deployment (e.g., whisper for old behavior).