Local speech-to-text with OpenAI Whisper CLI. Supports Chinese, English, 100+ languages with translation and summarization.
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 voice-recognition或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install voice-recognition⚠️ 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/voice-recognition/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: voice-recognition description: Local speech-to-text with OpenAI Whisper CLI. Supports Chinese, English, 100+ languages with translation and summarization. version: 1.0.0 ---
Local speech-to-text with OpenAI Whisper CLI.
# Chinese recognition
python3 /Users/liyi/.openclaw/workspace/scripts/voice识别_升级版.py audio.m4a
# Force Chinese
python3 /Users/liyi/.openclaw/workspace/scripts/voice识别_升级版.py audio.m4a --zh
# English recognition
python3 /Users/liyi/.openclaw/workspace/scripts/voice识别_升级版.py audio.m4a --en
# Translate to English
python3 /Users/liyi/.openclaw/workspace/scripts/voice识别_升级版.py audio.m4a --translate
# With summary
python3 /Users/liyi/.openclaw/workspace/scripts/voice识别_升级版.py audio.m4a --summarizealias voice="python3 /Users/liyi/.openclaw/workspace/scripts/voice识别_升级版.py"Then use:
voice ~/Downloads/audio.m4a --zhbrew install openai-whisperscripts/voice识别_升级版.py - Main scriptscripts/voice_tool_README.md - Documentation100+ languages including:
medium (balance of speed and accuracy)~/.cache/whisper安装 Voice Recognition 后，可以对 AI 说这些话来触发它
Help me get started with Voice Recognition
Explains what Voice Recognition does, walks through the setup, and runs a quick demo based on your current project
Use Voice Recognition to local speech-to-text with OpenAI Whisper CLI
Invokes Voice Recognition with the right parameters and returns the result directly in the conversation
What can I do with Voice Recognition in my design & creative workflow?
Lists the top use cases for Voice Recognition, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/voice-recognition/ 目录（个人级，所有项目可用），或 .claude/skills/voice-recognition/（项目级）。重启 AI 客户端后，用 /voice-recognition 主动调用，或让 AI 根据上下文自动发现并使用。
Voice Recognition 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Voice Recognition 可免费安装使用。请查阅仓库了解许可证信息。
Local speech-to-text with OpenAI Whisper CLI. Supports Chinese, English, 100+ languages with translation and summarization.
Voice Recognition 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 Voice Recognition
Identifies repetitive steps in your workflow and sets up Voice Recognition to handle them automatically