transcribe-anything SKILL.md skillA
transcribe-anything from swyxio/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add swyxio/skills/transcribe-anything@v1.1Pins v1.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- swyxio/skills
- Path
transcribe-anything/SKILL.md- Versions recorded
- 3
- Latest version
- v1.1, committed Jun 24, 2026
- First version recorded
- Mar 28, 2026
- Size
- 34,142 bytes
- Repository stars
- 194
- License
- MIT
Transcribes audio and video files to text using pluggable ASR backends. Default backend is local whisper/MLX Whisper for ASR. Supports pyannote.audio direct diarization, whisperX, insanely-fast-whisper, faster-whisper, whisper.cpp, OpenAI Whisper API, Groq Whisper API, Deepgram, AssemblyAI, Gemini, and Hugging Face models. Handles very long files (1-8+ hours) by preprocessing with ffmpeg: extracts audio from video, converts to optimal ASR format, detects and skips silence, and chunks for API…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Transcribe Anything Transcribes audio and video files to text. Pluggable backends, silence skipping for long files, optional speaker diarization, and multiple output formats. ## Setup ### Required (install these first) ```bash # ffmpeg — audio extraction, preprocessing, silence detection brew install ffmpeg # yt-dlp — downloading video/audio from URLs (optional but recommended) brew install yt-dlp # Default ASR backend — OpenAI's whisper CLI pip3 install --break-system-packages openai-whisper # Apple Silicon accelerated ASR, preferred when available uv tool install mlx-whisper ``` ### Recommended Extras ```bash # curl_cffi — prevents OAuth errors when downloading private videos pip3 install --break-system-packages curl_cffi # faster-whisper — 4x faster than whisper, built-in VAD silence skipping, lower memory # Best local backend for long files (1hr+) pip3 install --break-system-packages faster-whisper # pyannote.audio — preferred local diarization when HF_TOKEN is available uv venv --python 3.11 .venv-pyannote uv pip install --python .venv-pyannote/bin/python "pyannote.audio" soundfile # whisperX — adds precise word-level timestamps; diarization requires HF_TOKEN …
Read the whole file at its exact version.
How to install
mdr add swyxio/skills/transcribe-anything@sha256:1afa2c171f78d5b6The line at the top of this page pins the label v1.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7q2y27ldtoenl77i)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Mar 28, 2026 and Jun 24, 2026, about one every 44 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1 latest | 2026-06-24 | c64c327 | 34,142 B | A | view · diff |
| v1.0 | 2026-05-25 | 35b20fb | 22,988 B | A | view · diff |
| v1.0 | 2026-03-28 | 51195d3 | 22,988 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (34142 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
swyxio/skills · 194 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7q2y27ldtoenl77i GET https://markdownregistry.com/api/v1/resolve?ref=swyxio/skills/transcribe-anything GET https://markdownregistry.com/api/v1/blob/1afa2c171f78d5b6a724a6f4e0665fc027775d9463339d224394dbc10484f92f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.