Transcribe

该 Skill 通过 Docker 构建 whisper:local 镜像并安装 transcribe CLI，使用 faster-whisper 的 small 模型在本地把 mp3、m4a、ogg、wav、webm、flac、aac 音频转录为纯文本，默认西班牙语，可用 auto 自动识别，全程本地无需 API Key。

javicasper

热度 73.45

最近更新 2026-05-17 11:07:57

分类：效率依赖：代码执行 / 读写文件应用场景：文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add transcribe

Metadata

name: transcribe
description: 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.

Transcribe

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