# haoheliu/AudioLDM2

Text-to-Audio/Music Generation

Repository: https://github.com/haoheliu/AudioLDM2
Canonical: https://ross.abutalabs.com/products/audioldm2
Language: Python
License: NOASSERTION
License Family: other
Topics: audio-generation
Last push: 2024-09-29T15:05:21+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 80
- inputs: {"age_days": 1125, "days_push": 703, "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 2639, forks 211 (observed 2026-08-28T04:07:06.377060+00:00)

## What it is
AudioLDM 2 is a Python library and CLI for generating audio, music, and speech from text prompts using latent diffusion models. It includes a Gradio web app, Hugging Face Diffusers integration, and checkpoints up to 48kHz.

## Use cases
- generate sound effects from a text prompt
- create background music from a description
- text-to-speech with speaker description and transcription
- upscale low-quality audio with super resolution
- batch generate audio from a list of prompts
- integrate text-to-audio generation into a diffusers pipeline

## When to choose
- you need generative audio or music from text in Python
- you want both sound effects and TTS from one model
- you want a ready-made Gradio demo or CLI

## When to avoid
- you need real-time or low-latency audio synthesis
- you lack a GPU and need fast inference
- you need permissively licensed weights for commercial use without checking the custom license

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, machine-learning, deep-learning, tts
- domain: machine-learning, artificial-intelligence
- platform: python, cli
- tags: text-to-audio, text-to-music, latent-diffusion, gradio-web-app, diffusers-integration, sound-effects, speech-generation, audio, gpu

## Member repositories
- haoheliu/AudioLDM2 (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.377060+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 2026-08-30T02:19:09.661642+00:00, confidence not recorded.
  - readme: https://github.com/haoheliu/AudioLDM2 (fetched 2026-08-28T04:07:06.377060+00:00, sha ff1053ec1490)
  - registry_pypi: https://pypi.org/pypi/audioldm2/json (fetched 2026-08-29T10:02:09.929608+00:00, sha 4466f231e39c)
- Data as of 2026-08-30T08:39:29.467469+00:00.