whisper-sttFree local speech-to-text transcription using OpenAI Whisper. Transcribe audio files (mp3, wav, m4a, ogg, etc.) to text without API costs. Use when: (1) User...
Install via ClawdBot CLI:
clawdbot install nickylin/whisper-sttGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/openai/whisperAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Content creators and media producers can use this skill to transcribe podcasts, interviews, or video content for generating subtitles (SRT/VTT) to improve accessibility and SEO. It's ideal for converting voice memos into text for blog posts or scripts without incurring cloud API costs.
Researchers and students can transcribe lectures, interviews, or focus group recordings to text for analysis, note-taking, or creating study materials. The local processing ensures data privacy and avoids subscription fees, making it suitable for educational institutions.
Businesses and legal professionals can use this skill to transcribe meetings, depositions, or client calls into text for records, minutes, or evidence documentation. The ability to specify languages like Chinese with high-accuracy models supports multilingual environments.
Organizations focused on accessibility can generate subtitles for videos to comply with regulations like the ADA, enhancing content for deaf or hard-of-hearing audiences. The free local operation reduces costs for non-profits or small businesses.
Language learners and translators can transcribe audio in various languages to text for practice, analysis, or creating bilingual subtitles. The model selection allows balancing speed and accuracy for different proficiency levels.
Offer a basic free version for local transcription with limited models, then charge for cloud-based processing, advanced models (e.g., large-v3-turbo), or batch processing features. Revenue comes from subscriptions targeting businesses needing scalability.
License this skill as an embeddable component for other software platforms, such as video editors or CRM systems, charging per integration or based on usage volume. Focus on enterprises requiring custom language support or high-volume transcription.
Provide consulting services to help organizations implement and optimize this skill for specific use cases, such as legal transcription or multilingual subtitling. Offer custom model training or integration support for a one-time fee.
💬 Integration Tip
Ensure ffmpeg is installed for broad audio format support and use the large-v3-turbo model for a good balance of speed and accuracy in production environments.
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...