# haoheliu/AudioLDM

AudioLDM: Generate speech, sound effects, music and beyond, with text.

Repository: https://github.com/haoheliu/AudioLDM
Canonical: https://ross.abutalabs.com/products/audioldm
Homepage: https://audioldm.github.io/
Language: Python
License: NOASSERTION
License Family: other
Topics: audio-generation
Last push: 2025-06-25T20:07:37+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 28, release rhythm 35, longevity 93
- inputs: {"age_days": 1312, "days_push": 434, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2907, forks 271 (observed 2026-08-28T04:07:29.135506+00:00)

## What it is
AudioLDM is a Python library and research model for text-to-audio generation using latent diffusion models conditioned on CLAP embeddings. It generates speech, sound effects, and music from text, and supports audio-to-audio generation, style transfer, inpainting, and super-resolution.

## Use cases
- generate sound effects from a text description
- create background music from a prompt
- synthesize speech from text
- transfer the style of one audio to another using a text description
- do audio inpainting and super-resolution
- run a web app for text-to-audio generation

## When to choose
- you need to generate audio (speech, music, sound effects) from text prompts
- you want zero-shot text-guided audio manipulation like style transfer
- you want a research-grade text-to-audio model with a Gradio demo and CLI

## When to avoid
- you need production-grade, commercially licensed audio generation (license is non-standard)
- you need real-time or low-latency audio synthesis
- you only need text-to-speech with fine voice control

## Facets
- artifact type: library
- maturity: maintenance
- function: audio-processing, machine-learning, deep-learning
- domain: artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: text-to-audio, latent-diffusion, sound-effects, music-generation, speech-synthesis, style-transfer, gradio, audio, gpu

## Member repositories
- haoheliu/AudioLDM (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:29.135506+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 2026-08-30T07:34:23.702029+00:00, confidence not recorded.
  - readme: https://github.com/haoheliu/AudioLDM (fetched 2026-08-28T04:07:29.135506+00:00, sha 8b669303d07f)
  - homepage: https://audioldm.github.io/ (fetched 2026-08-29T09:49:38.782389+00:00, sha 912e55b9f06c)
  - registry_pypi: https://pypi.org/pypi/audioldm/json (fetched 2026-08-29T09:49:38.791914+00:00, sha ec1aead54d9a)
- Data as of 2026-08-30T08:39:29.467469+00:00.