VieNeu-TTS

🦜 1. Installation & Web UI

Quick Start

CPU (default) — torch-free, runs v3 Turbo via ONNX Runtime. Most users want this:

⚡On CPU the backbone runs int8 by default — ~1.6× faster and ~4× smaller than fp32, with voice quality preserved. Want maximum fidelity instead? Pass Vieneu(precision="fp32") (slower on CPU). precision only affects the CPU/ONNX path; on GPU it's ignored (PyTorch).

pip install vieneu

GPU (CUDA) — only if you have an NVIDIA GPU.

ℹ️ When is GPU actually worth it? The GPU win comes from batching, so it only pays off on long text (many chunks generated together in one forward — long-form or bulk synthesis). For short text the torch-free CPU/ONNX path is usually faster (there's no batch to fill, and no kernel-launch overhead). Use CPU for short, interactive calls; reach for GPU for long-form or high-throughput work.

pip install torch==2.8.0 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128
pip install "transformers==4.57.6"   # pinned — most stable transformers for the GPU SDK
pip install vieneu

import time
from vieneu import Vieneu

---

## 🐳 3. High-Quality Server (Standard Mode) <a name="docker-remote"></a>

Deploy VieNeu-TTS as a high-performance API Server (powered by LMDeploy) with a single command.

---

### 1. Run with Docker (Recommended)

**Requirement**: [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) is required for GPU support.

**Start the Server with a Public Tunnel (No port forwarding needed):**
```bash
docker run --gpus all -p 23333:23333 -v huggingface_cache:/root/.cache/huggingface pnnbao/vieneu-tts:latest --tunnel

• Default: The server loads the VieNeu-TTS-v2 model for maximum quality.
• Tunneling: The Docker image includes a built-in bore tunnel. Check the container logs to find your public address (e.g., bore.pub:31631).