Promote Sign in Sign up

Audio model

Confucius4-TTS

Confucius4-TTS is NetEase Youdao's open-source multilingual, cross-lingual zero-shot text-to-speech engine. It clones any voice from a short audio sample without needing a reference transcript, then speaks in any of 14 languages while preserving the speaker's identity and emotional tone, with both streaming and non-streaming synthesis modes.

Youdao Audio Open weights apache-2.0
Visit model website ↗ Hugging Face
Type
Audio
Weights
Open
Downloads
547
Likes
35
Pipeline
text to speech
License
apache-2.0

Model hub

netease-youdao/Confucius4-TTS

Repo
netease-youdao/Confucius4-TTS
Access
Public
Technical tags and languages
zh en ja ko de fr id vi th es pt it ru ms safetensors confucius4 text-to-speech tts speech-synthesis zero-shot voice-cloning cross-lingual multilingual llm
Open on Hugging Face

More from Youdao

3

About Youdao

1

Youdao is a NetEase intelligent-learning company offering digital learning services, language tools, educational applications, and smart learning devices.