netease-youdao / Confucius4-TTS
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
Why this job: says: tts; topics: text-to-speech, tts, speech-synthesis
What it does
Confucius4-TTS is an advanced LLM-based text-to-speech (TTS) system designed for multilingual and cross-lingual speech synthesis. Built on a speech encoder + large language model (LLM) architecture, Confucius4-TTS enables high-quality speech generation while preserving speaker identity across languages. You can try our online demo at https://huggingface.co/spaces/CharlesW/Confucius4-TTS.
Get started
git clone https://github.com/netease-youdao/Confucius4-TTS.git
cd Confucius4-TTS You need: Python 3.10; CUDA 12.6
- Maintenance
- Active
- Last commit 6 days ago
- Stars
- 858
- +9 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 25% closed
- 12 still open
- Pull requests
- 6 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| index-tts / index-tts | 25,010 | 42 days ago | Custom | No downloads |
| QwenAudio / CosyVoice | 24,347 | 5 months ago | Apache-2.0 | No downloads |
| RVC-Boss / GPT-SoVITS | 64,662 | yesterday | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- audio
- cross-lingual
- deep-learning
- fine-tuning
- multi-lingual
- python
- pytorch
- speech-synthesis
- text-to-speech
- tts
- voice-clone
- zero-shot-tts
Project record
- JobSpeech and audio
- StatusListed
- Commits41
- Forks88
- Watching5
- Stars in 28 days+25
- CreatedMay 19, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026