yumoqing df8aafe1d8 feat: add TTS and ASR audio API endpoints ...

- POST /v1/audio/speech (TTS): MiniMax Speech 2.6 Turbo/HD, 2.5 HD, F5-TTS local
- POST /v1/audio/transcriptions (ASR): qwen3-asr-flash, Nvidia parakeet
- Add comprehensive docs for both endpoints in API.md
- Update load_path.py RBAC (logined + customer roles)

2026-06-04 13:58:26 +08:00

..

audio

feat: add TTS and ASR audio API endpoints

2026-06-04 13:58:26 +08:00

chat/completions

refactor: V1 API 支持新 catelogid 缩写(t2t/t2v/t2i等)，向后兼容中文名

2026-05-30 20:36:16 +08:00

image/generations

refactor: V1 API 支持新 catelogid 缩写(t2t/t2v/t2i等)，向后兼容中文名

2026-05-30 20:36:16 +08:00

models

feat: add /v1/models/catelog endpoint - list models by catalog with exclude

2026-06-02 11:21:25 +08:00

music/generations

feat: add music generation API (MiniMax Music 2.5/2.6)

2026-06-04 13:40:08 +08:00

tasks

bugfix

2026-05-23 21:48:46 +08:00

video/generations

refactor: V1 API 支持新 catelogid 缩写(t2t/t2v/t2i等)，向后兼容中文名

2026-05-30 20:36:16 +08:00