/install wav-audio-transcribe
Audio Transcribe Skill
语音转文字,使用本地 Whisper 模型,完全离线、隐私安全。
前置条件
安装 Whisper(只需一次):
# macOS
brew install whisper
# 或者 Python 包(更推荐,自动装模型)
pip3 install openai-whisper
使用方法
基本转录(中文音频)
当用户说"转录这个音频"时,运行:
python3 ~/.openclaw/workspace/skills/audio-transcribe/scripts/transcribe.py "/path/to/audio.wav"
指定格式
# 输出 SRT 字幕
python3 ~/.openclaw/workspace/skills/audio-transcribe/scripts/transcribe.py "/path/to/audio.wav" srt
# 输出 JSON(含时间戳)
python3 ~/.openclaw/workspace/skills/audio-transcribe/scripts/transcribe.py "/path/to/audio.wav" json
# 指定语言
python3 ~/.openclaw/workspace/skills/audio-transcribe/scripts/transcribe.py "/path/to/audio.wav" txt zh
# 英文音频
python3 ~/.openclaw/workspace/skills/audio-transcribe/scripts/transcribe.py "/path/to/audio.wav" txt en
支持的格式
| 格式 | 说明 | 适用场景 |
|---|---|---|
txt |
纯文本(默认) | 快速阅读、存档 |
srt |
字幕文件 | 视频压制、外语学习 |
json |
结构化结果 | 二次处理、时间戳提取 |
支持的音频格式
.wav, .mp3, .m4a, .flac, .ogg, .opus, .mp4, .mov 等ffmpeg支持的格式
脚本参数
python3 transcribe.py \x3Caudio_file> [output_format] [language]
参数:
audio_file 音频文件路径(必填)
output_format 输出格式:txt, srt, json(默认: txt)
language 语言代码:zh, en, ja, ko 等(默认: 自动检测)
注意事项
- 首次运行会下载模型(~500MB),耐心等待
- 音频质量越高转录越准
- Whisper 模型可选:
tiny,base,small,medium,large,默认base - 如果想换模型,修改脚本中
whisper.load_model('base')为其他选项 - 长音频会自动分段处理
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wav-audio-transcribe - After installation, invoke the skill by name or use
/wav-audio-transcribe - Provide required inputs per the skill's parameter spec and get structured output
What is Audio Transcribe?
语音转文字 Skill。使用本地 Whisper (openai-whisper) 将音频文件转录为文本、字幕(SRT)或 JSON。适用于会议记录、播客转录、语音备忘录等场景。触发方式:转写音频、转录语音、音频转文字、语音转文本、whisper、生成字幕。 It is an AI Agent Skill for Claude Code / OpenClaw, with 44 downloads so far.
How do I install Audio Transcribe?
Run "/install wav-audio-transcribe" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Audio Transcribe free?
Yes, Audio Transcribe is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Audio Transcribe support?
Audio Transcribe is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Audio Transcribe?
It is built and maintained by SunnyTang (@ai-tesing); the current version is v1.0.0.