azzurra voice needs about 2.6 GB of memory at its main file (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Italian text‑to‑speech model with expressive, natural voice
`azzurra-voice` is a 1.65 billion‑parameter TTS model for Italian. It delivers 24,000 Hz speech with natural intonation and emotion. The model is open‑weight and can be run with `csm.rs` or the Hugging Face `transformers` library.
Good at
- Expressive Italian TTS
- High‑quality 24,000 Hz audio
- Fast real‑time inference with csm.rs
Limits
- No vision support
- Requires 2.6 GB VRAM at 8 k context
- License is CC Attribution‑NonCommercial‑ShareAlike
Best for
- Voice assistants in Italian
- Audiobook narration
- Multilingual TTS pipelines
Who it’s for. Developers building Italian language applications who need natural, expressive speech. Researchers exploring TTS models and makers of local AI solutions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.9 GB | 2.6 GB | Fits | Get file → |
The only available GGUF file is 1.86 GB with an estimated memory of 2.6 GB at 8 k context. This is suitable for systems with at least 4 GB VRAM. No other quantizations are provided, so use the full‑precision model if memory allows.
What GPU do you need for azzurra voice?
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 the main file (1.9 GB file, about 2.6 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about azzurra voice
How much VRAM does azzurra voice need?
About 2.6 GB at its main file with an 8K context window. That is the 1.9 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 azzurra voice on an 8 GB GPU?
Yes, with the smaller files: the 1.9 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of azzurra voice GGUF?
It depends on the quant: file is 1.9 GB.
Where can I download azzurra voice GGUF?
The files are on Hugging Face in the cartesia/azzurra-voice repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does azzurra voice use?
Hugging Face lists the license as cc. 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 azzurra-voice on 4 GB VRAM?
The model requires about 2.6 GB VRAM at 8 k context, so 4 GB VRAM is sufficient for inference.
Does azzurra-voice support other languages?
No, the model is trained exclusively for Italian.
Is azzurra-voice free to use?
Yes, it is released under a Creative Commons Attribution‑NonCommercial‑ShareAlike license.