whisper-mlx-localFree local speech-to-text for Telegram and WhatsApp using MLX Whisper on Apple Silicon. Private, no API costs.
Install via ClawdBot CLI:
clawdbot install impkind/whisper-mlx-localGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:8787/transcribeCalls external URL not in known-safe list
https://github.com/ImpKind/local-whisperAI Analysis
The skill runs entirely locally (localhost:8787) and processes audio on-device, consistent with its stated privacy purpose. The only external call is to a public GitHub repository for installation, which is expected and non-malicious.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Transcribes voice messages from Telegram chats locally on a Mac, eliminating API costs for users who frequently receive audio messages. Ideal for personal or small team communication where privacy and cost savings are priorities.
Converts audio notes from WhatsApp into text for easy reading and archiving, running entirely on-device to ensure data privacy. Useful for individuals or businesses handling sensitive conversations without relying on cloud services.
Translates spoken audio files from foreign languages into English while traveling, without needing an internet connection. Helps tourists or business travelers understand local audio content privately and cost-effectively.
Transcribes podcast episodes or audio recordings locally for content creators who prioritize data security and want to avoid subscription fees. Enables easy creation of show notes or subtitles without external APIs.
Converts lecture recordings or educational audio into text for students or educators, allowing offline access and reducing costs associated with transcription services. Supports learning environments where budget constraints exist.
Monetizes through donations, sponsorships, or premium support services for users who need help with setup or customization. Leverages the free tool to build a community and generate revenue from value-added services.
Offers licensed versions for businesses that require enhanced features, such as batch processing or integration with proprietary systems, while keeping the core tool free. Targets companies needing scalable, private transcription solutions.
Partners with Apple or Mac resellers to bundle the skill with new Mac purchases, promoting it as a value-added feature for privacy-conscious users. Generates revenue through referral fees or co-marketing agreements.
💬 Integration Tip
Ensure Python dependencies are installed and the daemon is running before configuring OpenClaw to avoid transcription failures.
Scored Jun 19, 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...