VieNeu-TTS-v2-Turbo-GGUF

> **Ultra-fast Vietnamese & English TTS — runs entirely on CPU, no GPU required.** [](https://opensource.org/licenses/Apache-2.0) [](https://github.com/pnnbao97/VieNeu-TTS) [](https://discord.gg/yJt8kzjzWZ) **VieNeu-TTS v2 Turbo** is the lightweight, CPU-optimized edition of the VieNeu-TTS family — a state-of-the-art Vietnamese Text-to-Speech system. Quantized to **GGUF** format and paired with an **ONNX** neural codec, this model delivers near-real-time speech synthesis on commodity hardware: laptops, edge devices, and even Raspberry Pi class machines. This repository hosts the **GGUF quantized weights** intended for use with `llama-cpp-python` as the inference backend, alongside the companion ONNX codec for waveform generation. - 🇻🇳🇺🇸 **Bilingual (Code-switching):** Naturally handles mixed Vietnamese–English sentences, powered by [sea-g2p](https://github.com/pnnbao97/sea-g2p). No need to pre-label language boundaries. - ⚡ **Extreme Speed:** Optimized GGUF quantization achieves real-time or faster inference on a standard CPU. - 💻 **Zero GPU Dependency:** Runs fully offline on any x86_64 / ARM64 machine with sufficient RAM. - 🔇 **AI Watermarking:** Audio output embeds an imperceptible identifier for responsible AI content tracing. - 🔊 **24 kHz Audio:** High-fidelity waveform output suitable for production applications. pip install vieneu pip install vieneu --extra-index-url https://pnnbao97.github.io/llama-cpp-python-v0.3.16/cpu/ pip install vieneu --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal/ from vieneu import Vieneu tts = Vieneu() text = "Hệ thống điện chủ yếu sử dụng alternating current because it is more efficient." audio = tts.infer(text=text) tts.save(audio, "output_Xuân Vĩnh.wav") print("💾 Saved to output_Xuân Vĩnh.wav") voices = tts.list_preset_voices() for desc, voice_id in voices: print(f"Voice: {desc} (ID: {voice_id})") my_voice_id = voices[1][1] if len(voices) > 1 else voices[0][1] # Giọng Phạm Tuyên voice_data = tts.get_preset_voice(my_voice_id) audio_custom = tts.infer(text="Tôi đang nói bằng giọng của Bác sĩ Tuyên.", voice=voice_data) tts.save(audio_custom, "output_Phạm Tuyên.wav") print("💾 Saved to output_Phạm Tuyên.wav") Clone any voice with only **3-5 seconds** of audio using the local Turbo engine: from vieneu import Vieneu tts = Vieneu() # Defaults to Turbo mode my_voice = tts.encode_reference("examples/audio_ref/example.wav") audio = tts.infer( text="Đây là giọng nói được clone trực tiếp bằng SDK của VieNeu-TTS.", voice=my_voice ) tts.save(audio, "cloned_voice.wav") git clone https://github.com/pnnbao97/VieNeu-TTS.git cd VieNeu-TTS uv sync # minimal install (Turbo/CPU) uv run vieneu-web VieNeu-TTS v2 Turbo is a two-stage TTS system: 1. **LLM Backbone (GGUF):** A transformer language model conditioned on text tokens and speaker embeddings. It predicts discrete audio codec tokens autoregressively. 2. **Neural Codec (ONNX):** A VQ-VAE-based neural codec ([VieNeu-Codec](https://huggingface.co/pnnbao-ump)) decodes the predicted token sequence into a 24 kHz waveform. The bilingual capability is enabled by `sea-g2p`, which converts mixed-language graphemes to phonemes before the LLM backbone processes them. The model was trained on over **20,000 hours** of combined Vietnamese and English speech data, covering a wide range of speakers, accents, recording conditions, and speaking styles. - [x] GGUF/ONNX Turbo engine - [x] Bilingual (Vietnamese–English) code-switching - [x] Turbo Voice Cloning - [ ] Mobile SDK (Android / iOS) - [ ] Streaming output API This model is released under the **Apache License 2.0** — free for personal and commercial use. *Made with ❤️ for the Vietnamese TTS community by [@pnnbao97](https://github.com/pnnbao97) and contributors.*