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.
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 transcribe或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install 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/transcribe/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- 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. ---
Local audio transcription using faster-whisper in Docker.
cd /path/to/skills/transcribe/scripts
chmod +x install.sh
./install.shThis builds the Docker image whisper:local and installs the transcribe CLI.
transcribe /path/to/audio.mp3 [language]es (Spanish)auto for auto-detectiontranscribe /tmp/voice.ogg # Spanish (default)
transcribe /tmp/meeting.mp3 en # English
transcribe /tmp/audio.m4a auto # Auto-detectmp3, m4a, ogg, wav, webm, flac, aac
transcribe scripts/transcribe - CLI wrapper (bash)scripts/install.sh - Installation script (includes Dockerfile inline)small (fast) - edit install.sh for large-v3 (accurate)安装 Transcribe 后，可以对 AI 说这些话来触发它
Help me get started with Transcribe
Explains what Transcribe does, walks through the setup, and runs a quick demo based on your current project
Use Transcribe to transcribe audio files to text using local Whisper (Docker)
Invokes Transcribe with the right parameters and returns the result directly in the conversation
What can I do with Transcribe in my design & creative workflow?
Lists the top use cases for Transcribe, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/transcribe/ 目录（个人级，所有项目可用），或 .claude/skills/transcribe/（项目级）。重启 AI 客户端后，用 /transcribe 主动调用，或让 AI 根据上下文自动发现并使用。
Transcribe 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Transcribe 可免费安装使用。请查阅仓库了解许可证信息。
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 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 Transcribe
Identifies repetitive steps in your workflow and sets up Transcribe to handle them automatically