🦜 VieNeu-TTS
VieNeu-TTS is an advanced on-device Vietnamese Text-to-Speech (TTS) with instant voice cloning and English–Vietnamese bilingual support. The SDK defaults to VieNeu-TTS v3 Turbo (48 kHz) and the minimal install is torch-free — on CPU it runs entirely on ONNX Runtime.
✨ Key Features
- v3 Turbo, 48 kHz — high-fidelity, natural Vietnamese speech (default).
- Torch-free on CPU — minimal install runs on ONNX Runtime; PyTorch is never imported.
- Built-in default voices — call them by name, no reference clip needed.
- Instant voice cloning — clone any voice from 3–5s of audio.
- Emotion cues (experimental) — drop
[cười],[thở dài],[hắng giọng]into the text. - Bilingual (En–Vi) code-switching, fully offline.
📦 Install
# Minimal, TORCH-FREE — runs v3 Turbo on CPU via ONNX Runtime
pip install vieneu
# Optional: GPU + older backends (v1/v2 PyTorch & GGUF, v3 Turbo on GPU)
pip install "vieneu[gpu]"
⚡ NVIDIA GPU acceleration for v3 Turbo (ONNX, torch-free)
To run the default v3 Turbo engine on an NVIDIA GPU without PyTorch, swap the
CPU ONNX Runtime for the GPU build. The two share the onnxruntime namespace and
conflict, so remove the CPU one first:
pip install vieneu
pip uninstall -y onnxruntime
pip install "onnxruntime-gpu>=1.20.0"
The engine auto-detects the GPU at runtime (falls back to CPU if absent) — no code change needed. Requires a compatible NVIDIA driver.
🚀 Quick Start (Python SDK)
from vieneu import Vieneu
# Default = v3 Turbo. CPU → ONNX (torch-free); GPU → PyTorch (auto-detected).
tts = Vieneu()
# 1. Default voice (Ngọc Lan) — 48 kHz, no reference needed
audio = tts.infer("Xin chào, đây là VieNeu-TTS phiên bản ba Turbo.")
tts.save(audio, "output.wav")
# 2. Built-in voices by name
for label, voice_id in tts.list_preset_voices():
print(label, voice_id)
audio = tts.infer("Mình là Xuân Vĩnh nè!", voice="Xuân Vĩnh")
# 3. Emotion / non-verbal cues — EXPERIMENTAL: [cười] [thở dài] [hắng giọng]
audio = tts.infer("Nghe hay quá đi [cười]. Để mình nói tiếp [hắng giọng].", voice="Ngọc Linh")
🦜 Zero-shot Voice Cloning
from vieneu import Vieneu
tts = Vieneu()
# Clone straight from a 3–5s clip — no reference transcript needed.
audio = tts.infer(text="Chào bạn, đây là giọng của tôi.", ref_audio="path/to/voice.wav")
tts.save(audio, "cloned.wav")
Older models (v1 / v2 — requires pip install "vieneu[gpu]")
tts = Vieneu(mode="standard") # v2 GGUF, bilingual, podcast
tts = Vieneu(mode="turbo") # v2 Turbo, fastest
🔬 Model Overview
| Model | Engine | Device | Sample Rate | Features |
|---|---|---|---|---|
| VieNeu-TTS v3 Turbo (default) | ONNX (CPU) / PyTorch (GPU) | CPU/GPU | 48 kHz | Default voices, cloning, emotion cues |
| VieNeu-TTS v2 | PyTorch / GGUF | GPU/CPU | 24 kHz | Bilingual, podcast ([gpu]) |
| VieNeu-TTS v1 | PyTorch | GPU/CPU | 24 kHz | Stable, Vietnamese ([gpu]) |
🤝 Support & Links
- GitHub: pnnbao97/VieNeu-TTS
- Discord: Join our community
Made with ❤️ for the Vietnamese TTS community
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vieneu-3.0.10.tar.gz.
File metadata
- Download URL: vieneu-3.0.10.tar.gz
- Upload date:
- Size: 1.1 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
012c149d2b96fcd5e708636f2081dcd9691c782961395b975ecff14b725fbee7
|
|
| MD5 |
bfc46c44229d5bd10b0801a30f14ca4d
|
|
| BLAKE2b-256 |
7b868fabe9c1ab917dfddb0970a9507e492156488513505fed4a072e35080cab
|
File details
Details for the file vieneu-3.0.10-py3-none-any.whl.
File metadata
- Download URL: vieneu-3.0.10-py3-none-any.whl
- Upload date:
- Size: 1.1 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fbaa448f9179749058bc3232f9eb528c9396b4d65a6152b2c36a3bdc27ea6536
|
|
| MD5 |
7c8cf599ab03d5f79c4d65f89d6bca46
|
|
| BLAKE2b-256 |
58c4b1e45b630a10624a734047f959a41719f4f64bdd42b6d8df40a8c49ff548
|
