{"skill":{"slug":"audio-recognition","displayName":"Audio Recognition","summary":"音频语音识别服务(Speech-to-Text)。当用户上传音频文件，需要将语音内容转换为文字，或需要识别音频中的特定信息（如关键词、歌曲名）时触发。 适用于：(1) 会议录音转写 (2) 音频内容提取 (3) 语音指令识别 (4) 音视频字幕生成","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":129,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1775165881342,"updatedAt":1775167618223},"latestVersion":{"version":"1.0.0","createdAt":1775165881342,"changelog":"- Initial release of the audio-recognition skill for speech-to-text tasks.\n- Supports accurate transcription of audio to text with speaker diarization.\n- Includes noise reduction, audio normalization, and multi-language recognition.\n- Features robust post-processing: punctuation, error correction, and optional timestamps.\n- Suitable for meeting transcriptions, subtitle generation, voice command recognition, and content extraction.","license":"MIT-0"},"metadata":null,"owner":{"handle":"zzhimin","userId":"s17eh2vm73czsfq06qnh0rrxg583wswr","displayName":"zzhimin","image":"https://avatars.githubusercontent.com/u/71487698?v=4"},"moderation":null}