# lucidrains/soundstorm-pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Repository: https://github.com/lucidrains/soundstorm-pytorch
Canonical: https://ross.abutalabs.com/products/soundstorm-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, audio-generation, deep-learning, non-autoregressive, transformers, attention-mechanism
Last push: 2025-04-24T14:36:52+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 18, release rhythm 40, longevity 86
- inputs: {"age_days": 1204, "days_push": 496, "days_rel": 496, "gap_med": 0.0, "n_releases_24m": 11}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1546, forks 94 (observed 2026-08-28T04:05:01.551659+00:00)

## What it is
A PyTorch implementation of SoundStorm, Google DeepMind's efficient parallel audio generation model that applies MaskGiT-style masked generation to residual vector-quantized audio codes using a Conformer transformer. It is a research library for training and generating audio non-autoregressively in a small number of steps.

## Use cases
- generate audio in parallel with a non-autoregressive transformer
- train a SoundStorm model on residual VQ audio codes
- implement MaskGiT-style iterative demasking for audio tokens
- build a text-to-speech pipeline with SoundStream and semantic TTS models
- experiment with Conformer architectures for audio token generation

## When to choose
- you want an open PyTorch implementation of the SoundStorm paper
- you need fast parallel audio generation instead of slow autoregressive decoding
- you already have SoundStream/EnCodec codes or want to train end-to-end on raw audio

## When to avoid
- you need a production-ready, polished TTS service with pretrained voices
- you want a simple inference-only text-to-speech tool without training
- you need non-Python environments or non-PyTorch frameworks

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, audio-processing, tts
- domain: artificial-intelligence, deep-learning, speech-processing
- platform: python
- tags: audio-generation, soundstorm, maskgit, conformer, non-autoregressive, pytorch, research-implementation, audio

## Member repositories
- lucidrains/soundstorm-pytorch (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:01.551659+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 2026-08-30T04:30:34.139473+00:00, confidence not recorded.
  - readme: https://github.com/lucidrains/soundstorm-pytorch (fetched 2026-08-28T04:05:01.551659+00:00, sha de47f1912280)
  - registry_pypi: https://pypi.org/pypi/soundstorm-pytorch/json (fetched 2026-08-29T11:31:46.751056+00:00, sha f05f1cbef333)
- Data as of 2026-08-30T08:39:29.467469+00:00.