{"skill":{"slug":"byted-voice-to-text","displayName":"Byted Voice To Text","summary":"语音转文字（ASR）。使用火山引擎 BigModel ASR 识别语音，包含极速版（≤2h/100MB 同步快速返回）和标准版（≤5h 异步识别）两种模式。支持飞书语音消息、本地音频文件及音频 URL。当收到语音消息或音频附件（.ogg/.mp3/.wav）时使用本技能。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":101,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774597118325,"updatedAt":1774600009299},"latestVersion":{"version":"1.0.0","createdAt":1774597118325,"changelog":"byted-voice-to-text 1.0.0 – Initial Release\n\n- Provides voice-to-text conversion using Volcengine BigModel ASR, supporting both Express (≤2h/100MB, synchronous) and Standard (≤5h, asynchronous) modes.\n- Supports Feishu voice messages, local audio files, and audio URLs (.ogg/.mp3/.wav).\n- Enforces mandatory script routing and error handling procedures; does not fall back to whisper or other providers.\n- Includes pre-checks for audio properties and ffmpeg/ffprobe dependencies, with auto-installation if missing.\n- Outlines precise instructions, environment variable requirements, and command samples for all supported workflows.","license":"MIT-0"},"metadata":{"os":["darwin","linux"],"systems":null},"owner":{"handle":"volcengine-skills","userId":"s17bcxs73bckd3eercvtn6cmsx83g5kg","displayName":"volcengine-skills","image":"https://avatars.githubusercontent.com/u/260939792?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1774600009299}}