VieNeu-TTS-v2
pnnbao-ump/VieNeu-TTS-v2
A popular open text-to-speech model, with 78.5K downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
about this model
Overview
VieNeu-TTS-v2 is a Vietnamese text-to-speech model optimized for natural communication, podcast-style multi-speaker conversations, and bilingual English-Vietnamese code-switching. It is trained on over 10,000 hours of bilingual data and supports zero-shot voice cloning from as little as 3–5 seconds of audio.
Key Strengths
- High-fidelity bilingual speech generation with seamless code-switching between English and Vietnamese.
- Multi-speaker conversation support with distinct voices and emotional nuances (natural and storytelling modes).
- Instant voice cloning from a short reference audio clip (3–5 seconds).
- Two model variants: VieNeu-TTS-v2 (PyTorch, GPU/CPU, highest quality) and VieNeu-TTS-v2 (GGUF Q4) (CPU-optimized for low latency).
Reference Voices
| File | Gender | Accent | Description |
|---|---|---|---|
| Bình | Male | North | Male voice, North accent |
| Tuyên | Male | North | Male voice, North accent |
| Nguyên | Male | South | Male voice, South accent |
| Hương | Female | North | Female voice, North accent |
| Ngọc | Female | North | Female voice, North accent |
| Đoan | Female | South | Female voice, South accent |
Model Variants
| Model | Format | Device | Quality | Features |
|---|---|---|---|---|
| VieNeu-TTS-v2 | PyTorch | GPU/CPU | Highest | Podcast, En-Vi code-switching |
| VieNeu-TTS-v2 (GGUF) | GGUF Q4 | CPU | High | Fastest CPU, Podcast |
| VieNeu-TTS-v1 | PyTorch | GPU | High | Stable (Vietnamese only) |
| VieNeu-TTS-0.3B | PyTorch | GPU/CPU | Good | Legacy ultra-fast |
As a hosted API on gigarouter, this model is available via an OpenAI-compatible endpoint. No local installation or GPU required — simply call the API with text and optional parameters to generate speech.
We're benchmarking and onboarding VieNeu-TTS-v2 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.