---
license: other
library_name: vokra
tags:
  - vokra
  - gguf
---

# xtts-v2 (Vokra GGUF)

Converted to the Vokra GGUF format for [Vokra](https://github.com/ayutaz/vokra), a zero-dependency speech-AI inference runtime.

**This is a conversion, not a new model.** The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see *Source* below.

## Files

| File | Size | SHA-256 |
|---|---|---|
| `model.gguf` | 1989.3 MB | `a789da752b2e4e0e8f9bc0c9b2a04de22afffebc5d93bef85b5f04101f6de279` |

## Usage

```bash
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o model.gguf \
  https://huggingface.co/vokra/xtts-v2/resolve/main/model.gguf
```

```bash
vokra-cli run --model model.gguf --input input.wav
```

## Provenance

| Field | Value |
|---|---|
| Architecture | `xtts` |
| Tensors | 1095 |
| Upstream source | coqui/XTTS-v2 (Coqui multilingual zero-shot GPT-2 + DVAE + HiFi-GAN, coqui-public-model-license) |
| Upstream licence | `coqui-public-model-license` |
| Licence class | `non-commercial` |
| Registry model id | `xtts-v2` |
| Vokra GGUF schema | 1 |
| Converted by | vokra-core 0.1.0-alpha.0 |

Every row above is read out of this file's own `vokra.*` metadata, so the card cannot claim something the artifact does not carry.

## Licence

The weights are distributed under **coqui-public-model-license**, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

> The Hugging Face `license:` tag is set to `other` because `coqui-public-model-license` is not one of Hugging Face's accepted tag values. The authoritative licence is the one named above and reproduced in the `LICENSE` file — not the tag.

### ⛔ Non-commercial — you may not use this weight commercially

The upstream weight is **coqui-public-model-license**. It is republished here so the model can be evaluated and used for research, and the licence is unchanged by conversion.

- **Do not use this in a commercial product or service.** That restriction is upstream's, not Vokra's, and Vokra cannot waive it.
- Vokra's engine is Apache-2.0 and imposes no such limit — the limit is on **this weight**. Other models in this organisation are permissively licensed; check each one's card.
- Vokra's runtime refuses to load a non-commercial weight unless an explicit research flag is set, so this restriction is enforced at load time rather than left to the reader.

## Verifying this file

```bash
shasum -a 256 model.gguf
# expect: a789da752b2e4e0e8f9bc0c9b2a04de22afffebc5d93bef85b5f04101f6de279
```