VieNeu-TTS and Kani-TTS-Vie

These are competing Vietnamese TTS solutions from the same author, with VieNeu-TTS offering more advanced features (voice cloning, real-time CPU inference) while Kani-TTS-Vie prioritizes speed and efficiency with a smaller 370M parameter model.

VieNeu-TTS
73
Verified
Kani-TTS-Vie
51
Established
Maintenance 25/25
Adoption 10/25
Maturity 13/25
Community 25/25
Maintenance 10/25
Adoption 8/25
Maturity 13/25
Community 20/25
Stars: 894
Forks: 303
Downloads: —
Commits (30d): 105
Language: Python
License: Apache-2.0
Stars: 64
Forks: 28
Downloads: —
Commits (30d): 0
Language: Jupyter Notebook
License: Apache-2.0
No Package No Dependents
No Package No Dependents

About VieNeu-TTS

pnnbao97/VieNeu-TTS

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

Employs a modular architecture with multiple inference backends: GGUF/ONNX-based Turbo mode for CPU execution, and PyTorch variants for GPU-accelerated synthesis with voice cloning. Supports bilingual English-Vietnamese code-switching via [sea-g2p](https://github.com/pnnbao97/sea-g2p) phoneme conversion, and offers both lightweight SDK integration and remote API deployment via Docker/LMDeploy for scalable inference without client-side GPU requirements.

About Kani-TTS-Vie

pnnbao97/Kani-TTS-Vie

Fast Vietnamese TTS. 370M params, 3-second inference.

Scores updated daily from GitHub, PyPI, and npm data. How scores work