.VoiceTut-TTS-gguf-root needs about 2.0 GB of memory at Q8_0 (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.4 GB (Q8_0) to 1.6 GB (F16).
VoiceTut-TTS: Egyptian Arabic TTS with code‑switching and zero‑shot cloning
VoiceTut-TTS is a text‑to‑speech model fine‑tuned from OmniVoice for Egyptian Arabic. It supports Arabic‑English code‑switching, 19 built‑in voices, zero‑shot voice cloning, and true streaming for long text.
Good at
- Egyptian Arabic TTS
- Arabic↔English code‑switching
- Zero‑shot voice cloning
Limits
- No vision support
- Requires --language arz flag
- Large VRAM for high‑quality inference
Best for
- Voice assistants in Egypt
- Accessibility tools for Arabic speakers
- Creative content with custom voice cloning
Who it’s for. Developers building Arabic‑centric speech applications. Researchers needing a fine‑tuned Egyptian TTS model. Content creators wanting customizable voices.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.4 GB | 2.0 GB | Fits | Get file → | |
| F16 | 1.6 GB | 2.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q8_0 (1.35 GB, ~2 GB RAM). For 12 GB VRAM, F16 (1.64 GB, ~2.3 GB RAM) offers higher precision. Memory estimates are approximate.
What GPU do you need for .VoiceTut-TTS-gguf-root?
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 (1.6 GB file, about 2.3 GB in use).
Which .VoiceTut-TTS-gguf-root quant should you choose?
Q8_0 (1.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about .VoiceTut-TTS-gguf-root
How much VRAM does .VoiceTut-TTS-gguf-root need?
About 2.0 GB at Q8_0 with an 8K context window. That is the 1.4 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 .VoiceTut-TTS-gguf-root on an 8 GB GPU?
Yes, with F16: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of .VoiceTut-TTS-gguf-root GGUF?
It depends on the quant: Q8_0 is 1.4 GB, F16 is 1.6 GB.
Where can I download .VoiceTut-TTS-gguf-root GGUF?
The files are on Hugging Face in the mohammedaly22/VoiceTut-TTS-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does .VoiceTut-TTS-gguf-root 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 VoiceTut-TTS on 8 GB VRAM?
Yes, the Q8_0 quant uses 1.35 GB file size and needs about 2 GB VRAM at 8k context.
Does the model support voice cloning?
Yes, zero‑shot cloning is supported with a few seconds of reference audio.
What language ID must I use?
Always pass --language arz to match the Egyptian Arabic training.