🎬

Transcribe

Very Easy

Transcribe audio files to text using local Whisper (Docker). Use when receiving voice messages, audio files (.mp3, .m4a, .ogg, .wav, .webm), or when asked to transcribe audio content.

Install

🤖Use in AI Agents

Claude Code

# Install Skill (downloads SKILL.md to .claude/skills/)
clawhub install transcribe

# Then just tell Claude: "use Transcribe to help me..."

OpenAI Codex / Cursor / Windsurf

# Same install command — works with all SKILL.md-compatible AI coding tools
clawhub install transcribe

OpenClaw Ecosystem

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.).

Environment & Dependencies

🟢

Very Easy

Fully free & local — no account, no GPU needed

Runs Locally

No internet required — data never leaves your machine

SKILL.md

Local audio transcription using faster-whisper in Docker.

Installation

cd /path/to/skills/transcribe/scripts
chmod +x install.sh
./install.sh

This builds the Docker image whisper:local and installs the transcribe CLI.

Usage

transcribe /path/to/audio.mp3 [language]

Default language: es (Spanish)
Use auto for auto-detection
Outputs plain text to stdout

Examples

transcribe /tmp/voice.ogg          # Spanish (default)
transcribe /tmp/meeting.mp3 en     # English
transcribe /tmp/audio.m4a auto     # Auto-detect

Supported Formats

mp3, m4a, ogg, wav, webm, flac, aac

When Receiving Voice Messages

Save the audio attachment to a temp file
Run transcribe <path>
Include the transcription in your response
Clean up the temp file

Files

scripts/transcribe - CLI wrapper (bash)
scripts/install.sh - Installation script (includes Dockerfile inline)

Notes

Model: small (fast) - edit install.sh for large-v3 (accurate)
Fully local, no API key needed

Code Example

clawhub transcribe meeting_recording.wav && cat meeting_recording.txt

Also popular in Video Editing

View all

Openai Whisper

clawhubVideo Editing Medium

3.9

OpenAI Whisper：使用 Whisper 模型进行视频语音识别和转录。

815

clawhub install openai-whisper

Mlx Whisper

clawhubVideo Editing Very Easy

3.6

Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).

clawhub install mlx-whisper

🖥️ Canvas-OS

clawhubVideo Editing Easy

3.5

Canvas as an app platform. Build, store, and run rich visual apps on the OpenClaw Canvas.

clawhub install canvas-os

Blender

clawhubVideo Editing Easy

3.5

Avoid common Blender mistakes — transform application, modifier order, UV seams, and export settings for game engines.

clawhub install blender

Canvas Design

Skills.shVideo Editing Very Easy

3.5

Create beautiful visual art in .png and .pdf documents.

22K

npx skills add anthropics/skills@canvas-design

Media Writing

clawhubVideo Editing Easy

3.4

You are a professional media writing expert with extensive experience in creating engaging and impactful content across multiple formats. Creating attention-...

clawhub install media-writing