Menu
Speech-to-text transcription using Whisper API or local engine
Generate and compare multiple implementation variants with benchmarking and scoring
Advanced browser automation for AI agents with snapshot-ref interaction pattern - navigate, snapshot interactive elements with refs, click/fill/select by refs, manage sessions, and extract structured data
Design RESTful APIs with best practices, conventions, and OpenAPI specs
Generate API documentation from code - produce OpenAPI/Swagger specs, Markdown API references, request/response examples, and interactive documentation from source code analysis
Universal API gateway - connect to 100+ APIs with a unified interface, manage API keys, and chain API calls
API测试技能 - IPC处理器发现、测试生成、健康检查、回归测试
| name | audio-transcriber |
| display-name | Audio Transcriber |
| description | Speech-to-text transcription using Whisper API or local engine |
| version | 1.0.0 |
| category | media |
| user-invocable | true |
| tags | ["audio","speech","transcription","whisper","stt"] |
| capabilities | ["speech-to-text","multi-language","format-output"] |
| supported-file-types | ["mp3","wav","m4a","ogg","flac","webm"] |
| os | ["win32","darwin","linux"] |
| handler | ./handler.js |
| tools | ["file_read","file_write"] |
| instructions | Use this skill to transcribe audio files to text using Whisper API or local engines. Supports multiple output formats (text, SRT, JSON) and languages. |
| examples | [{"input":"/audio-transcriber --transcribe meeting.mp3","output":"Transcribed 45 minutes of audio to text"},{"input":"/audio-transcriber --transcribe lecture.wav --format srt","output":"Generated SRT subtitle file from audio"}] |
| author | ChainlessChain |
Speech-to-text transcription using Whisper API or local engines.
/audio-transcriber --transcribe <file> [--format txt|srt|json] [--language <lang>]
/audio-transcriber --info <file>
/audio-transcriber --providers
| Provider | Requirements |
|---|---|
| Whisper API | OpenAI API key (OPENAI_API_KEY) |
| Local | Local whisper binary or Ollama |
fluent-ffmpeg — Audio preprocessing