sopro v2 turbo needs about 0.9 GB of memory at F16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Lightweight 120M‑parameter TTS model with streaming and zero‑shot voice cloning
Sopro v2 turbo is a 120M‑parameter text‑to‑speech model that streams with ~300 ms time‑to‑first‑audio on a laptop CPU. It supports English, European Portuguese, French, and German, and can clone voices from 5‑20 seconds of reference audio.
Good at
- Fast streaming on CPU
- Zero‑shot voice cloning
- Multilingual support
Limits
- Requires sopro>=2.2.0 or @soprotts/onnx-web>=0.3.0
- No vision support
- Limited to 8 k context for the provided quant
Best for
- Voice‑cloning demos
- Browser‑based TTS applications
- Low‑resource TTS deployment
Who it’s for. Developers and researchers needing a small, efficient TTS model that runs on a laptop CPU or in the browser. The model is open‑source under Apache‑2.0 and supports multiple European languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.3 GB | 0.9 GB | Fits | Get file → |
The only available quant is F16, 0.32 GB in size, estimating 0.9 GB of VRAM at 8 k context. This is suitable for machines with at least 1 GB of VRAM. No other quantizations are provided.
What GPU do you need for sopro v2 turbo?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (0.3 GB file, about 0.9 GB in use).
Which sopro v2 turbo quant should you choose?
F16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about sopro v2 turbo
How much VRAM does sopro v2 turbo need?
About 0.9 GB at F16 with an 8K context window. That is the 0.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run sopro v2 turbo on an 8 GB GPU?
Yes, with F16: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sopro v2 turbo GGUF?
It depends on the quant: F16 is 0.3 GB.
Where can I download sopro v2 turbo GGUF?
The files are on Hugging Face in the samuel-vitorino/sopro-v2-turbo repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does sopro v2 turbo use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Sopro v2 turbo on a laptop with 8 GB VRAM?
Yes, the F16 quant uses about 0.9 GB of VRAM at 8 k context, well within an 8 GB budget.
Does the model support voice cloning in the browser?
Yes, a fully in‑browser demo is available and runs via ONNX runtime, though low‑memory devices may crash.
What languages can the model speak?
English, European Portuguese, French, and German are supported.