{"skill":{"slug":"jiadong-assembly-large-audio","displayName":"Assembly Large Audio Transcriber","summary":"Transcribe large audio files (100MB+, up to 1GB/12 hours) with speaker diarization. Uses AssemblyAI API with direct HTTP calls. Supports MP3, WAV, M4A, FLAC,...","tags":{"audio":"1.0.0","chinese":"1.0.0","large-file":"1.0.0","latest":"1.0.0","speech":"1.0.0","transcription":"1.0.0"},"stats":{"comments":0,"downloads":133,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1775745783363,"updatedAt":1775746007819},"latestVersion":{"version":"1.0.0","createdAt":1775745783363,"changelog":"- Initial release of assembly-large-audio-transcriber skill.\n- Transcribes large audio files (100MB–1GB, up to 12 hours) with speaker diarization using AssemblyAI API via HTTP calls.\n- Supports MP3, WAV, M4A, FLAC, OGG, and WEBM formats with no SDK dependencies (only requires `requests`).\n- Provides word-level timestamps, multi-language support (auto-detection), and detailed output including speaker and time segmentation.\n- Includes robust error handling and guidance for API limits and file splitting.\n- Output can be archived to a specified directory with structured Markdown or JSON formatting.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"jiadong0723","userId":"s171evqrw320fst1p7x7dqf9hs84gww5","displayName":"jiadong0723","image":"https://avatars.githubusercontent.com/u/267246555?v=4"},"moderation":null}