Stable Audio Open

2wks agoupdate 00
Collect 0

Open-source model for generating short audio samples and sound effects from text.

Collection time:
2023-12-11
Open siteMobile view
Stable Audio OpenStable Audio Open
Stable Audio OpenOpen site

What is Stable Audio Open?

Stable Audio Open is an open source model optimised for generating short audio samples, sound effects and production elements using text prompts. It allows anyone to generate up to 47 seconds of high-quality audio data from a simple text prompt. Its specialised training makes it ideal for creating drum beats, instrument riffs, ambient sounds, foley recordings and other audio samples for music production and sound design.

How to use Stable Audio Open?

To use Stable Audio Open, download the model from Hugging Face, install the required dependencies (torch, torchaudio, stable_audio_tools, einops), import the necessary libraries, load the model, generate audio using text prompts, and save the output as a WAV file.

Stable Audio Open’s Core Features

Open Source Model Specialized Training for high-quality audio generation Customizable with user’s own data Generates up to 47 seconds of audio

Stable Audio Open’s Use Cases

  • Creating drum beats
  • Generating instrument riffs
  • Producing ambient sounds
  • Designing foley recordings
  • Developing audio samples for music production

Relevant Navigation