jimmy-claw-mlx-whisperSet up mlx-whisper as the local audio transcription engine for OpenClaw on Apple Silicon Macs (M1/M2/M3/M4). Automatically transcribes voice notes sent via T...
Install via ClawdBot CLI:
clawdbot install yinghaojia/jimmy-claw-mlx-whisperGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 21, 2026
Users on Apple Silicon Macs can automatically transcribe voice notes from messaging apps like Telegram or WhatsApp for personal documentation, note-taking, or task management. This enables offline processing without relying on cloud APIs, ensuring privacy and reducing costs for individual users who handle sensitive or frequent audio content.
Journalists and researchers can use this skill to transcribe interviews or field recordings locally on their Macs, avoiding internet dependencies and maintaining confidentiality. It supports multiple languages and models for balancing speed and accuracy, making it ideal for on-the-go transcription in remote or secure environments.
Content creators, such as podcasters or video producers, can generate transcripts for audio content to improve accessibility with captions or subtitles. Running locally on Apple Silicon ensures fast processing without API limits, allowing for batch transcription of episodes or clips while keeping data private.
Small businesses or support teams can transcribe customer voice messages from platforms like WhatsApp in multiple languages for record-keeping or analysis. The local setup eliminates subscription fees for transcription services and integrates seamlessly with existing OpenClaw workflows for automated response handling.
Students and educators can transcribe lectures or study recordings on their Macs to create searchable text notes. The skill's offline capability is useful in classrooms with limited internet, and customizable models allow tuning for academic accuracy across different subjects and languages.
Offer a free basic version with the default small model, then charge for premium features like larger models (e.g., medium or large), batch processing, or advanced language support. Revenue comes from one-time purchases or subscriptions for power users in industries like media or research.
Provide consulting or setup services to integrate this skill into corporate workflows, such as customer support or internal communication systems. Charge for customization, training, and ongoing support, targeting small to medium businesses that need offline, secure transcription without cloud dependencies.
Partner with Apple or resellers to bundle this skill with Mac hardware, marketing it as a value-added feature for professionals like journalists or creators. Revenue is generated through licensing fees per device or as part of premium software packages for enhanced productivity tools.
💬 Integration Tip
Ensure Python3 and pip3 are installed, and carefully follow the wrapper script setup to avoid path errors in OpenClaw configuration.
Scored Jun 17, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...