Transcribe Anything

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 size limits. Supports speaker diarization, word-level timestamps, custom vocabulary, and multiple outpu

201 stars 12 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add swyxio/skills --skill transcribe-anything
Manual install
git clone --depth 1 https://github.com/swyxio/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/transcribe-anything ~/.claude/skills/transcribe-anything

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 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
# Bundles faster-whisper + pyannote alignment/diarization
pip3 install --break-system-packages whisperx
```

**pyannote/whisperX diarization setup** (one-time):
1. Create a Hugging Face account at https://huggingface.co
2. Accept the terms for these gated models:
Read the full skill on GitHub

Details

Skill name
transcribe-anything
Repository
swyxio/skills
Path
transcribe-anything/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Transcribe Anything skill do?

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 size limits. Supports speaker diarization, word-level timestamps, custom vocabulary, and multiple outpu

How do I install the Transcribe Anything skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add swyxio/skills --skill transcribe-anything. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Transcribe Anything popular?

It lives in swyxio/skills, which has 201 GitHub stars and 12 forks.

Related skills

Accelevents API

201

swyxio/skills

Use when reading or updating AI Engineer Europe speaker records through the Accelevents REST API, especially for full-record PUT updates, auth header quirks, and preserving existing speaker fields.

Software Development12

Accelevents Speaker Sync

201

swyxio/skills

Use when website speaker, session, schedule, room, track, or headshot changes must be synchronized back to Accelevents for AI Engineer Europe 2026.

AI, LLMs & Agents12

Agents SDK

201

swyxio/skills

Build or debug stateful applications that specifically use Cloudflare's `agents` package, including Agent classes, routing, callable methods, synchronized state, scheduling, AIChatAgent, durable execution, or Agents SDK client hooks. Do not trigger for generic AI-agent design, the OpenAI Agents SDK, or ordinary Durable Object work that does not use the Cloudflare Agents SDK.

AI, LLMs & Agents12

Transcription to Content

150

guia-matthieu/clawfu-skills

Transform podcast transcripts into multiple content assets—blog posts, social snippets, newsletters, and SEO-optimized landing pages—using systematic repurposing workflows. Use when: Maximizing ROI from podcast episodes; Creating blog content from audio/video; Generating social media posts from long-form content; Building newsletter content from transcripts; Extracting quotes and highlights for promotion

Images, Video & AudioIn 1 list32

Sync Accelevents

201

swyxio/skills

Use when pulling Accelevents speaker headshots, social data, bios, and schedule metadata into the AI Engineer Europe source data and photo assets.

Images, Video & Audio12

Vhs

228

pproenca/dot-skills

VHS terminal recording best practices from Charmbracelet (formerly charmbracelet-vhs). This skill should be used when writing, reviewing, or editing VHS tape files to create professional terminal GIFs and videos. Triggers on tasks involving .tape files, VHS configuration, terminal recording, demo creation, or CLI documentation.

Images, Video & Audio19

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.