Model reference · open weights

neucodec

Available as managed deployment Audio aoiandroid · community Audio→audio 1 variants 532 dl/mo

neucodec is an open-weight audio or speech model from aoiandroid. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byaoiandroid
TypeAudio & music
TaskAudio→audio
Released2026-05-02
Popularity532 downloads / month
LicenceOpen weights

About

What neucodec is

Distill-NeuCodec is a version of NeuCodec with a compatible, distilled encoder.

The distilled encoder is 10x smaller in parameter count and uses ~7.5x less MACs at inference time.

The distilled model makes the following adjustments to the model:

Our work is largely based on extending the work of X-Codec2.0 and SQCodec.

Read the full model card
  • Developed by: Neuphonic
  • Model type: Neural Audio Codec
  • License: apache-2.0
  • Repository: https://github.com/neuphonic/neucodec
  • Paper: arXiv
  • Pre-encoded Datasets:

Get Started

Use the code below to get started with the model.

To install from pypi in a dedicated environment, using Python 3.10 or above:

conda create -n neucodec python=3.10
conda activate neucodec
pip install neucodec

Then, to use in python:

import librosa
import torch
import torchaudio
from torchaudio import transforms as T
from neucodec import DistillNeuCodec

model = DistillNeuCodec.from_pretrained("neuphonic/distill-neucodec")
model.eval().cuda()

y, sr = torchaudio.load(librosa.ex("libri1"))
if sr != 16_000:
    y = T.Resample(sr, 16_000)(y)[None, ...] # (B, 1, T_16)

with torch.no_grad():
    fsq_codes = model.encode_code(y)
    # fsq_codes = model.encode_code(librosa.ex("libri1")) # or directly pass your filepath!
    print(f"Codes shape: {fsq_codes.shape}")
    recon = model.decode_code(fsq_codes).cpu() # (B, 1, T_24)

torchaudio.save("reconstructed.wav", recon[0, :, :], 24_000)

Training Details

The model was trained using the same data as the full model, with an additional distillation loss (MSE between distilled and original encoder ouputs).

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys aoiandroid-neucodec for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (aoiandroid-neucodec below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="aoiandroid-neucodec" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms