Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt
VieNeu-TTS is the next generation of on-device Vietnamese TTS: 10,000+ hours of bilingual training, instant voice cloning, a dedicated Podcast/Conversation mode, and extremely fast — real-time streaming with first audio in ~115 ms, RTF ≈ 0.01–0.02 batched on a consumer GPU (RTX 3060), ~2× real-time on a plain CPU (benchmarks).
The vieneu SDK defaults to VieNeu-TTS v3 Turbo (48 kHz). The minimal install is torch-free: on CPU everything runs on ONNX Runtime (PyTorch is never imported), and on a CUDA machine it auto-switches to the PyTorch engine — where inference is batched automatically (same API, no code change).
deep-learningon-device-mlreal-timespeech-synthesistext-to-speechttsvietnamesevietnamese-language
- Stars
- 3290
- Forks
- 1010
- Language
- Python
- License
- Apache-2.0
- Last push
- Nov 12, 2026
- Created
- Oct 28, 2025
Description and README excerpt from pnnbao97/VieNeu-TTS on GitHub ↗.