pnnbao97 /VieNeu-TTS
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
★ 3,386⑂ 1,034👁 48⑃ 142● 74▤ 40
+18
日增长
3,386
stars
1,034
forks
48
watchers
142
prs
74
issues
40
releases
README
🦜 VieNeu-TTS
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).
[!IMPORTANT]
🦜 VieNeu-TTS v4 — available on vieneu.io
VieNeu-TTS v4 delivers near-original voice cloning fidelity, allowing a short reference clip to be reproduced with very high speaker similarity.
Due to the strength of its voice-cloning capabilities and the potential for misuse, v4 is proprietary and will not be open-sourced. It is available exclusively through the VieNeu API / vieneu.io.
VieNeu-TTS v3 Turbo remains the latest open-source version available in this repository. Future open-source releases, including potential v3.x updates, may also be published here.
[!NOTE]
🦜 VieNeu-TTS v3 Turbo is officially released!
A brand-new architecture designed and trained from scratch by Phạm Nguyễn Ngọc Bảo (codec: MOSS-Audio-Tokenizer-Nano; phonemizer: sea-g2p):
- 48 kHz high-fidelity audio (up from 24 kHz).
- 25 built-in preset voices (10 editors' picks) — stable and consistent, no reference clip needed.
- Natural reading style everywhere — the style follows the reference voice (the style argument is deprecated and ignored).
- Emotion / non-verbal cues (experimental): drop [cười], [thở dài], [hắng giọng] straight into the text.
- Batched generation (batch size up to 32), including a multi-speaker Conversation mode that batches the whole script regardless of speaker.
- Instant voice cloning from a 3–8s clip, with automatic reference denoising.
- Real-time streaming + OpenAI-compatible API + Docker — POST /v1/audio/speech drop-in for the OpenAI SDK / Pipecat / LiveKit; first audio in ~115 ms and 16 concurrent streams under 200 ms on a single RTX 3060 (32 max), CPU-only streaming too. See §3, §4 Benchmarks and docs/streaming.md.
- LoRA fine-tuning — train your own voice or reading style on one consumer GPU (§5).
Try it in the Web UI (backbone "VieNeu-TTS-v3-Turbo") or the SDK (Vieneu(mode="v3turbo"), the default).
🎬 Demos
[!TIP]
Dubbing, Lecture, Tiktok Reel and Audiobook features are exclusively available in the official VieNeu App. This GitHub repository only provides a simplified Gradio demo interface and the core SDK for developers.
Voice Cloning
Dubbing
Tiktok Reel
Dubbing / Conversation
Lecture
📌 Table of Contents
1. 🦜 Installation & Web UI
2. 📦 Using the Python SDK
3. 🐳 API Server & Docker — OpenAI-compatible streaming API (v3 Turbo) · legacy v2 server
4. 📊 Benchmarks — every speed / latency number in one place (CPU vs GPU, batch, streaming, Nano)
5. 🎓 Fine-tuning (LoRA)
6. 🔬 Model Overview
7. 🚀 Roadmap
8. 🤝 Support & Contact
9. 📑 Top issues
#213English TTS generates unrequested speech after sentence end — native FP32 reproduction2 comments · 2026-10-12#219Bị lặp âm thanh1 comments · 2026-10-26#200thời gian cloned audio1 comments · 2026-09-18#199Audio đọc `50.000đ/cp` thành "năm mươi nghìn địa chỉ pê" — lỗi tiền tố `đ/c` ở sea-g2p1 comments · 2026-09-12#192[Thank you] create vi- full-duplex benchmark using the technology1 comments · 2026-08-28#189Run vieneu on AMD1 comments · 2026-08-10#178[Feature request] Hỗ trợ đọc công thức toán LaTeX/ký hiệu toán bằng tiếng Việt1 comments · 2026-07-17#120Pronounciation speed1 comments · 2026-03-26
Discussions
#172Prefix Caching: ❌1 comments · 2026-07-06#166Chào Bảo, mình đang nghiên cứu công nghệ nhép miệng 3d cho tiếng Việt muốn xin nguồn dữ liệu âm thanh từ Bảo để train không biết được không.0 comments · 2026-06-28#122VieNeu-TTS has a page on Shypd (AI Tool Directory)0 comments · 2026-03-30#99[Request] Dataset Format Reference for VieNeu-TTS-1000h1 comments · 2026-03-04#98How to prepare/label stylistic data for VieNeu-TTS (Styles & Non-verbal cues)?1 comments · 2026-03-04#97Subject: Enhancing VieNeu-TTS with Style & Emotional Control Tags2 comments · 2026-03-04#62Welcome to VieNeu-TTS Discussions!1 comments · 2026-01-10
Latest release
VieNeu Desktop App for Windows (v0.18.25) app-v0.18.25 2026-11-12Bản VieNeu Desktop 0.18.25: Tạo hàng loạt đọc thẳng tệp phụ đề .srt. Chọn nhiều tệp và một giọng, nhận về lời thoại được đọc liền mạch, bỏ hết mốc thời gian. Dùng được cả V3 (trên máy) lẫn V4 (khoá API). Lồng tiếng có thêm nút đi thẳng tới đó. VieNeu Desktop 0.18.25: Batch now reads .srt subtitle files directly. Pick several files and one voice, and get the dialogue read as continuous speech with every timecode dropped. Works with V3 (on this computer) and V4 (API key). Dubbing gets a button that goes straight there. Tải về / Download - Windows x64: VieNeu_0.18.25_x64-setup.exe — 94.630.6