菜单
Free local speech-to-text for Telegram and WhatsApp using MLX Whisper on Apple Silicon. Private, no API costs.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill whisper-mlx-local命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
| name | whisper-mlx-local |
| description | Free local speech-to-text for Telegram and WhatsApp using MLX Whisper on Apple Silicon. Private, no API costs. |
| metadata | {"openclaw":{"emoji":"🎤","version":"1.5.0","author":"Community","repo":"https://github.com/ImpKind/local-whisper","requires":{"os":["darwin"],"arch":["arm64"],"bins":["python3"]},"install":[{"id":"deps","kind":"manual","label":"Install dependencies","instructions":"pip3 install -r requirements.txt"}]}} |
Transcribe voice messages for free on Telegram and WhatsApp. No API keys. No costs. Runs on your Mac.
Voice transcription APIs cost money:
If you transcribe a lot of Telegram voice messages, it adds up.
This skill runs Whisper locally on your Mac. Same quality, zero cost.
tools.media.audio config with the one belowpip3 install -r requirements.txt
python3 scripts/daemon.py
First run will download the Whisper model (~1.5GB). Wait for "Ready" message.
Add this to your ~/.openclaw/openclaw.json:
{
"tools": {
"media": {
"audio": {
"enabled": true,
"models": [
{
"type": "cli",
"command": "~/.openclaw/workspace/skills/local-whisper/scripts/transcribe.sh",
"args": ["{{MediaPath}}"],
"timeoutSeconds": 60
}
]
}
}
}
}
openclaw gateway restart
Now voice messages from Telegram, WhatsApp, etc. will be transcribed locally for free!
./scripts/transcribe.sh voice_message.ogg
Instead of paying for OpenAI API to transcribe incoming voice messages, point OpenClaw to this local daemon. Free transcription forever.
cp com.local-whisper.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.local-whisper.plist
Daemon runs at localhost:8787:
curl -X POST http://localhost:8787/transcribe -F "file=@audio.ogg"
# {"text": "Hello world", "language": "en"}
Any language → English:
./scripts/transcribe.sh spanish_audio.ogg --translate
MIT