{"skill":{"slug":"feishu-minimax-t2a-voice","displayName":"feishu-minimax-t2a-voice","summary":"飞书语音消息收发：接收语音自动转文字（飞书原生 Transcript + Whisper 降级），回复语音由 MiniMax T2A 合成后发送。","tags":{"latest":"1.0.1"},"stats":{"comments":1,"downloads":117,"installsAllTime":0,"installsCurrent":0,"stars":1,"versions":2},"createdAt":1775241788656,"updatedAt":1775470907009},"latestVersion":{"version":"1.0.1","createdAt":1775469936845,"changelog":"Version 1.0.1 - Changelog\n\n- Added scripts/reply.py to support generating voice message replies.\n- Updated documentation to reflect simplified usage: now reply generation is `python scripts/reply.py \"<文字内容>\"`.\n- Documented support for both MiniMax T2A (mp3 → opus) and Edge TTS (ogg) as audio generation backends, with automatic fallback.\n- Explained how to insert MiniMax prosody tags and fillers to make synthesized speech more natural.\n- Revised environment variable requirements: MINIMAX_API_KEY is now optional; will use Edge TTS if unavailable.\n- Clarified sending method: produced `.opus` or `.ogg` should be sent as `audio/opus` via Feishu.","license":"MIT-0"},"metadata":null,"owner":{"handle":"michelangelo-in-sistine","userId":"s174kt6n4txq2cf0ez7nvc92c1845szh","displayName":"habitum","image":"https://avatars.githubusercontent.com/u/19338350?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1775470907009}}