Опишете задачата
Към всички skills

audio-transcription

mitsuhiko · Данни и AI

Transcribe local audio/video and Apple Voice Memos quickly with cached MLX Whisper models, including bad/low-quality audio.

Оригинален текст · няма потвърден превод на български
Платформи: Не са посочениНиво: Не е посоченоВ индекса: 22.09.2026 г.Обновен в GitHub: 06.09.2026 г.

Първо прочетете инструкцията.

Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.

Оригинален SKILL.md
GitHub хранилище
Звезди на репото
3147
Лиценз
Apache-2.0
Последна проверка на записа
22.09.2026 г.

Добавете в своя инструмент.

Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.

npx skills add mitsuhiko/agent-stuff

Страницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.

Откъс от SKILL.md

Началото на файла на автора, без превод.

Use this skill whenever the user asks to transcribe an audio/video file, a Voice Memos export, dictation, lecture, meeting recording, or "bad audio".

Core rules

  1. Preserve temporary inputs immediately. Voice Memo share-sheet paths under ~/Library/Containers/com.apple.VoiceMemos/Data/tmp/.com.apple.uikit.itemprovider... can disappear. Before probing or experimenting, copy the file to stable /private/tmp/audio-transcription-inputs/.
  2. Use cached local models, not cloud APIs. Prefer MLX Whisper via uvx --from mlx-whisper mlx_whisper; Hugging Face models must be cached in ~/.cache/huggingface/hub/.
  3. Force language when known. For Armin's own dictations this is usually English with an Austrian/German accent, even when the filename is German. Do not infer language from filename alone.
  4. For bad audio, run a hallucination-resistant pass. Use --condition-on-previous-text False, --word-timestamps True, and --hallucination-silence-threshold 2.
  5. Deliver a cleaned best-effort transcript. Compare model output with timestamps/JSON, remove obvious Whisper loops, and mark uncertain spans as [unclear] rather than inventing words.

Fast path

Run from this skill directory:

cd /Users/mitsuhiko/Development/agent-stuff/skills/audio-transcription
./transcribe-audio.py "/path/to/audio.m4a" --language en --quality balanced

The script:

  • stages a stable copy of the input under /private/tmp/audio-transcription-inputs/
  • ensures the selected model is cached (downloads only if missing)
  • writes txt, srt, vtt, tsv, and json to /private/tmp/audio-transcriptions/<name>-<timestamp>/
  • detects obvious hallucination loops and, in balanced mode, reruns with the full model if needed

Useful variants:

# Quick draft, fastest cached model
./transcribe-audio.py audio.m4a --language en --quality fast

# Bad/important audio, slower full model
./transcribe-audio.py audio.m4a --language en --quality best \
  --prompt "Armin Ronacher dictating about AI, data centers, Vienna, Donauinsel, shareholder value."

# Auto language detection when language is genuinely unknown
./transcribe-audio.py audio.m4a --language auto --quality balanced

Cached models

Default model IDs:

  • Fast/balanced: mlx-community/whisper-large-v3-turbo
  • Best fallback: mlx-community/whisper-large-v3-mlx

Pre-cache / refresh both models:

Целият SKILL.md в GitHub