Voice Transcribe
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
clawhub install voice-transcribeA skill that automatically transcribes podcast audio content into text.
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install podcast-transcribe # Then just tell Claude: "use Podcast Transcribe to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install podcast-transcribe
This Skill is compatible with the OpenClaw standard. After installation, a SKILL.md file is auto-generated, usable by any OpenClaw-compatible AI Agent (Claude Code, Cursor, Windsurf, etc.).
./out/<episode-slug>/.npx podcast-helper transcribe <input> --output-dir <dir> --json.--progress jsonl only when machine-readable progress is needed..srt, and .txt.dist/cli.js exists, node dist/cli.js ... is acceptable. Do not default to repository-local build steps outside this repository.
If you are inside this repository and dist/cli.js is missing, run pnpm run build before using the repo-local entry point.npx, then pnpm dlx, then a globally installed podcast-helper.yt-dlp.mlx-whisper runs require ffmpeg, python3, and a working runtime from podcast-helper setup mlx-whisper.*.cleaned.txt.npx podcast-helper transcribe <input> --output-dir ./out/<slug> --json
pnpm dlx podcast-helper transcribe <input> --output-dir ./out/<slug> --jsonpodcast-helper transcribe <input> --output-dir ./out/<slug> --jsonnode dist/cli.js transcribe <input> --output-dir ./out/<slug> --json only inside this repositorynpx podcast-helper transcribe <input> --engine mlx-whisper --output-dir ./out/<slug> --json
curl https://r.jina.ai/<podcast-url>.*.cleaned.txt file.references/inputs-and-engines.md for supported inputs, engine selection, and dependency notes.references/output-contract.md for the JSON success and failure envelopes and progress handling.references/cleanup.md for detailed cleanup rules and conservative editing guidance.references/verification.md for smoke-test inputs and verification steps.references/setup.md when installing this skill into Claude Code, OpenClaw, or other agents.podcast-transcribe --input interview.m4a --language zh-CN --output-format srt --speaker-detection trueCreate chapters, highlights, and show notes from podcast audio or transcripts. Use when a user wants chapter markers, highlight clips, or show-note drafts without publishing or distribution actions.
clawhub install podcast-chaptering-highlights