QwenAudio/CosyVoice
22,620 2,607PythonApache-2.0Updated 5 months ago
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
audio-generationcantonesechatbotchatgptchinesecosyvoicecross-lingualenglishfine-grainedfine-tuninggpt-4ojapanesekoreanmulti-lingualnatural-language-generationpythontext-to-speechttsvoice-cloning
Our verdict: worth keeping an eye on
Provides a state‑of‑the‑art multilingual TTS model that could be repurposed for his local AI voice work, but its large size and heavy dependencies make it less immediately installable as a lightweight building block
Filed under text to speech in our directory.