# archinetai/audio-diffusion-pytorch

Audio generation using diffusion models, in PyTorch.

Repository: https://github.com/archinetai/audio-diffusion-pytorch
Canonical: https://ross.abutalabs.com/products/audio-diffusion-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, audio-generation, deep-learning, denoising-diffusion
Last push: 2023-06-12T22:40:16+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1518, "days_push": 1178, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2096, forks 176 (observed 2026-08-28T04:06:13.257092+00:00)

## What it is
A PyTorch library for audio generation using diffusion models, supporting unconditional and text-conditional generation, diffusion autoencoding, upsampling, and vocoding. It provides a generic, customizable U-Net, diffusion methods, and samplers that work on waveform and other data formats.

## Use cases
- generate audio with diffusion models in pytorch
- train a text-to-audio generation model
- build a diffusion autoencoder for audio
- upsample low-resolution audio with a diffusion model
- implement a custom diffusion sampler for non-audio data
- denoise audio waveforms with a u-net diffusion model

## When to choose
- you want a flexible, code-level PyTorch library for building and training audio diffusion models
- you need text-conditional audio generation with T5 embeddings and classifier-free guidance
- you want generic diffusion components reusable across data dimensions and formats

## When to avoid
- you need pre-trained models ready for inference - none are provided here
- you want a high-level tool with GUI or one-click audio generation
- you need maintained, frequently updated software - the last release was mid-2023

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, audio-processing, llm-training
- domain: deep-learning, artificial-intelligence, machine-learning
- platform: python
- tags: diffusion-models, audio-generation, text-to-audio, pytorch, generative-audio, unet, denoising-diffusion, audio

## Member repositories
- archinetai/audio-diffusion-pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:13.257092+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:54:35.418577+00:00, confidence not recorded.
  - readme: https://github.com/archinetai/audio-diffusion-pytorch (fetched 2026-08-28T04:06:13.257092+00:00, sha dc968e24d104)
  - registry_pypi: https://pypi.org/pypi/audio-diffusion-pytorch/json (fetched 2026-08-29T10:34:56.233892+00:00, sha e7792c62ed04)
- Data as of 2026-08-30T08:39:29.467469+00:00.