Model reference · open weights
VieNeu-TTS is an open-weight audio or speech model from pnnbao-ump, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
🦜 VieNeu-TTS v3 Turbo [](https://github.com/pnnbao97/VieNeu-TTS) [](https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo) [](https://pypi.org/project/vieneu/) [](https://discord.gg/yJt8kzjzWZ) Overview VieNeu-TTS v3 Turbo is the next generation of Vietnamese TTS — 48 kHz high-fidelity speech, 20 built-in preset voices across three regions (North / Central / South), instant voice cloning, real-time streaming, inline emotion cues, and seamless bilingual (En–Vi) code-switching. The reference implementation is the vieneu Python SDK (v3.3.0). Its 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 with automatic batching — same API, no code change. [!IMPORTANT] What's new in SDK v3.3.0: - 20 preset voices covering North / Central / South, both genders and several reading characters. - Torch-free voice cloning on CPU — cloning, denoising and addvoice now work on the ONNX-only install (kaldi-native-fbank + soxr), no PyTorch needed. - int8 backbone by default on CPU — ~1.6× faster and ~4× smaller than fp32 with quality preserved; use Vieneu(precision="fp32") for max fidelity. - Sliding-window repetition penalty for more stable long generations. 🏗️ Architecture & Credits The VieNeu-TTS v3 Turbo architecture is an original design by the author, Phạm Nguyễn Ngọc Bảo, and is trained from scratch on ~10,000 hours of English–Vietnamese speech — it is not a fine-tune, distillation, or adaptation of any existing TTS model. - Model architecture & training: designed and trained from scratch by Phạm Nguyễn Ngọc Bảo — https://github.com/pnnbao97 - Audio codec: MOSS-Audio-Tokenizer-Nano (OpenMOSS-Team) — 48 kHz neural audio codec. - Phonemizer: sea-g2p — fast Vietnamese/English grapheme-to-phoneme, also by the author. Tác giả: Phạm Nguyễn Ngọc Bảo 🔥 Quick Start (Web UI) - Option 1: CPU & macOS (minimal, torch-free) — recommended — runs v3 Turbo via ONNX ⚡ Use uv sync, not pip install, for the fastest CPU inference — it reproduces the locked environment with the optimized ONNX Runtime build. On Apple Silicon this ONNX/CPU path is faster than the MPS/PyTorch build. - Option 2:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | pnnbao-ump |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 131M |
| Variants | 2 |
| Released | 2026-06-05 |
| Popularity | 426k downloads / month |
| Likes | 56 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys vieneu-tts for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vieneu-tts below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="vieneu-tts" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗