使用 Fast-Whisper 和可选 Whisper 模型在本地自动转录语音消息,无需 API 密钥。
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install audio-transcribe或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install audio-transcribe⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/audio-transcribe/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
Auto-transcribe voice messages using faster-whisper (local, no API key needed).
pip install faster-whisper
Models download automatically on first use.
python3 /root/clawd/skills/audio-transcribe/scripts/transcribe.py /path/to/audio.ogg
Edit transcribe.py and change:
model = WhisperModel('small', device='cpu', compute_type='int8') # Options: tiny, base, small, medium, large-v3
| Model | Size | VRAM/RAM | Speed | Use Case | |-------|------|----------|-------|----------| | tiny | 39 MB | ~1 GB | ⚡⚡⚡ | Quick drafts | | base | 74 MB | ~1 GB | ⚡⚡ | Basic accuracy | | small | 244 MB | ~2 GB | ⚡ | Recommended | | medium | 769 MB | ~5 GB | 🐢 | Better accuracy | | large-v3 | 1.5 GB | ~10 GB | 🐢🐢 | Best accuracy |
Clawdbot auto-transcribes incoming voice messages when this skill is enabled.
scripts/transcribe.py — Main transcription scriptSKILL.md — This file安装 音频转录 后,可以对 AI 说这些话来触发它
Help me get started with Audio Transcribe
Explains what Audio Transcribe does, walks through the setup, and runs a quick demo based on your current project
Use Audio Transcribe to auto-transcribe voice messages locally using faster-whisper with se...
Invokes Audio Transcribe with the right parameters and returns the result directly in the conversation
What can I do with Audio Transcribe in my design & creative workflow?
Lists the top use cases for Audio Transcribe, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/audio-transcribe/ 目录(个人级,所有项目可用),或 .claude/skills/audio-transcribe/(项目级)。重启 AI 客户端后,用 /audio-transcribe 主动调用,或让 AI 根据上下文自动发现并使用。
音频转录 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
音频转录 可免费安装使用。请查阅仓库了解许可证信息。
使用 Fast-Whisper 和可选 Whisper 模型在本地自动转录语音消息,无需 API 密钥。
音频转录 属于「Design & Creative」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my design & creative tasks using Audio Transcribe
Identifies repetitive steps in your workflow and sets up Audio Transcribe to handle them automatically