archinetai/audio-diffusion-pytorch

Health v2 · maintenance only

Adoption not part of the score

2096 stars · 176 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning audio-processing llm-training deep-learning artificial-intelligence machine-learning python diffusion-models audio-generation text-to-audio pytorch generative-audio unet denoising-diffusion audio

Member repositories

For agents

markdown · JSON · MCP: product_card(name="archinetai/audio-diffusion-pytorch")