Voice To Text

该 Skill 运行本地 transcribe.py 脚本，调用 Vosk 离线语音识别把语音消息或音频文件转成文本。需自行安装 ffmpeg 与 vosk 包并下载模型；支持 MP3、WAV、M4A、OGG、FLAC、AAC、WEBM 等格式，音频先转为 16kHz 单声道 WAV，可通过环境变量指定模型，识别过程离线。

vae999

热度 39.76

最近更新 2026-05-11 17:26:03

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 voice-to-text

Metadata

name: voice-to-text
version: 1.0.0
description: Convert voice messages and audio files to text using Vosk offline speech recognition. Use when a user sends a voice message, audio file, or asks to transcribe speech to text.
homepage: https://alphacephei.com/vosk/
metadata: {"openclaw":{"emoji":"🎤","os":["darwin","linux"],"requires":{"bins":["ffmpeg"],"python":["vosk"]},"install":[{"id":"brew-ffmpeg","kind":"brew","formula":"ffmpeg","bins":["ffmpeg"],"label":"Install ffmpeg via Homebrew"},{"id":"pip-vosk","kind":"pip","package":"vosk","label":"Install Vosk via pip"}]}}

Voice to Text

Convert voice messages and audio files to text using Vosk, an offline speech recognition toolkit.

Setup

Install dependencies:

# macOS
brew install ffmpeg
pip install vosk

# Linux
apt-get install ffmpeg
pip install vosk

Download a Vosk model:

mkdir -p ~/.vosk/models && cd ~/.vosk/models

# Chinese (small, fast)
curl -LO https://alphacephei.com/vosk/models/vosk-model-small-cn-0.22.zip
unzip vosk-model-small-cn-0.22.zip

# English (small)
curl -LO https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip
unzip vosk-model-small-en-us-0.15.zip

Usage

When the user provides a voice message or audio file path, run the transcription:

python3 ~/skills/voice-to-text/transcribe.py "<audio_file_path>"

For specific model selection, set the environment variable:

VOSK_MODEL_PATH=~/.vosk/models/vosk-model-cn-0.22 python3 ~/skills/voice-to-text/transcribe.py "<audio_file_path>"

Supported Audio Formats

MP3, WAV, M4A, OGG, FLAC, AAC, WEBM
Voice messages from WeChat, Telegram, WhatsApp, etc.

Available Models

Model	Language	Size	Notes
vosk-model-small-cn-0.22	Chinese	42M	Fast, good accuracy
vosk-model-cn-0.22	Chinese	1.3G	High accuracy
vosk-model-small-en-us-0.15	English	40M	Fast, good accuracy
vosk-model-en-us-0.22	English	1.8G	High accuracy

Download models from: https://alphacephei.com/vosk/models

Example Workflow

User sends a voice message via WeChat/Telegram
OpenClaw receives the audio file
Run: python3 transcribe.py /path/to/voice.ogg
Return transcribed text to user

Troubleshooting

No model found: Download a model to ~/.vosk/models/
ffmpeg not found: Install via brew install ffmpeg or apt install ffmpeg
Poor accuracy: Try a larger model for better results

Notes

Works completely offline after model download
Supports multiple languages (download appropriate model)
Audio is converted to 16kHz mono WAV for processing