pnnbao-ump / text-to-speech Open weights updated 1 month ago

VieNeu-TTS-v3-Turbo

Name: VieNeu-TTS-v3-Turbo
Author: pnnbao-ump

VieNeu-TTS v3 Turbo is the next generation of Vietnamese TTS — 48 kHz high-fidelity speech, 23 built-in preset voices across three regions (North / Central / South), instant voice cloning, real-time streaming with an OpenAI-compatible API (16 concurrent streams on one RTX 3060), inline emotion cues, and seamless bilingual (En–Vi) code-switching.

Params

131 M

Context

1,024

Downloads 30d

2.1 M

Likes

106

Commercial use: allowed apache-2.0 Not gated GGUF · SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 103 days

▲ 1.1 M in the last 30 days (111.8%)

2.1 M306 K

Jul 31Sep 3Oct 7Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
vieneu-v3-turbo-q8_0.gguf	Q8_0	0.2 GB	0.7 GB	✅ Runs comfortably
vieneu-v3-turbo-bf16.gguf	GGUF	0.3 GB	0.8 GB	✅ Runs comfortably
model.safetensors	bf16	0.5 GB	1.1 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: VieNeuV3TurboForTTS
Parameters: 131 M
Tensor type: BF16
Context length: 1,024
Layers / heads: 12 / 12
Licence: apache-2.0
First seen on the Hub: 2026-06-05
Training datasets: pnnbao-ump/VieNeu-TTS-10k-ENVI
Added to our catalog: 2026-07-31

Compare with any text-to-speech model

Popular comparisons

Kokoro-82M 12.5 M audio.cpp-gguf 8.9 M XTTS-v2 5.7 M chatterbox 2.4 M F5-TTS 1.3 M Qwen3-TTS-GGUF 1.2 M

Appears in

Best open-source TTS