---
license: mit
library_name: vokra
tags:
  - vokra
  - gguf
  - neural-audio-codec
---

# dac-16khz (Vokra GGUF)

Neural audio codec model, 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 |
|---|---|---|
| `dac-16khz.gguf` | 283.8 MB | `7e631db79a05ad8b083d39231ac655efb1f7824eb277aacf44c59e9b2754192f` |

## Usage

```bash
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o dac-16khz.gguf \
  https://huggingface.co/vokra/dac-16khz/resolve/main/dac-16khz.gguf
```

```bash
# This artifact is consumed by another engine rather than run
# standalone — see the Vokra docs for the CODEC pipeline.
```

## Provenance

| Field | Value |
|---|---|
| Architecture | `dac` |
| Tensors | 358 |
| Upstream source | descriptinc/descript-audio-codec GitHub release (prepared via dac_prepare_checkpoint.py) |
| Upstream licence | `MIT` |
| Licence class | `permissive` |
| Registry model id | `dac` |
| 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 **MIT**, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

## Verifying this file

```bash
shasum -a 256 dac-16khz.gguf
# expect: 7e631db79a05ad8b083d39231ac655efb1f7824eb277aacf44c59e9b2754192f
```