whisper-cppInstall and use whisper.cpp (local, free/offline speech-to-text) with OpenClaw. Supports downloading different ggml model sizes (tiny/base/small/medium/large...
Install via ClawdBot CLI:
clawdbot install TrueNight/whisper-cppGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://huggingface.co/ggerganov/whisper.cpp/resolve/mainAudited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Content creators receive voice notes from collaborators or fans via Telegram and need to transcribe them for blog posts, subtitles, or social media content. This skill enables local, offline transcription without relying on paid APIs, ensuring privacy and cost savings while handling various audio formats.
Remote teams use Telegram for quick voice updates or meeting recordings that require transcription for documentation or accessibility. This skill provides a free, offline solution to convert these voice notes into text, avoiding subscription fees and maintaining data security within the organization.
Language learners or educators send voice notes via Telegram for pronunciation practice or assignments that need transcription for feedback. This skill supports multiple languages and model sizes, allowing accurate, local transcription without internet dependency, ideal for personalized learning tools.
Healthcare professionals use Telegram for quick voice memos on patient observations or administrative tasks that must be transcribed into electronic health records. This skill offers a secure, offline transcription method to protect sensitive data and reduce reliance on external services.
Journalists capture voice notes during interviews or on-site reporting via Telegram and need fast transcription for articles or archives. This skill enables local processing with customizable model accuracy, ensuring timely, cost-effective transcription without cloud-based delays or fees.
Offer the core skill for free to attract users, then provide paid services for advanced model tuning, language support, or integration with other platforms. Revenue comes from consulting fees or premium support packages for businesses needing optimized performance.
License this skill to companies for embedding into their internal tools or customer-facing applications, such as CRM systems or educational platforms. Charge based on usage tiers or per-seat licenses, with revenue generated from enterprise contracts and ongoing maintenance fees.
Bundle the skill with specialized hardware like local servers or IoT devices designed for offline audio processing. Sell these packages to industries like healthcare or security where data privacy is critical, generating revenue from product sales and optional service agreements.
💬 Integration Tip
Ensure ffmpeg and build tools are installed before setup, and test the wrapper directly with sample audio to verify configuration before relying on it for production use.
Scored Apr 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...