开箱即用的本地私有化部署语音服务,快速搭建Qwen3ASR/FunASR与Qwen3TTS/CosyVoice后端
-
Updated
Jul 6, 2026 - Python
开箱即用的本地私有化部署语音服务,快速搭建Qwen3ASR/FunASR与Qwen3TTS/CosyVoice后端
LightTTS is a lightweight TTS inference framework optimized for CosyVoice2 and CosyVoice3, enabling fast and scalable speech synthesis in Python and supports stream and bistream modes.
CosyVoice2 API server built with FastAPI, featuring efficient voice caching, queue-based request handling, and multi-request concurrency management.
Privacy-first Codex Skill for authorized local voice cloning with CosyVoice2, pronunciation control, prosody guidance, and QA—no per-call API fee.
A text-to-speech service built with CosyVoice2, with multi-node concurrency capabilities.
Add a description, image, and links to the cosyvoice2 topic page so that developers can more easily learn about it.
To associate your repository with the cosyvoice2 topic, visit your repo's landing page and select "manage topics."