Stable Audio Open

What it does

Stable Audio is a generative AI tool developed by Stability AI for creating music and sound effects. It allows users to generate high-quality audio in 44.1 kHz stereo from a text prompt and a specified duration, supporting both text-to-audio and audio-to-audio generation.

How to use: Users can create music and sound effects by inputting text prompts describing the desired audio. Additionally, users can add audio alongside text to experiment with style transfers and create variations.

Core features

• ✦Text-to-audio generation
• ✦Audio-to-audio generation
• ✦High-quality audio output (44.1 kHz stereo)
• ✦Commercial usage rights

Use cases

• →Generating original music for commercial projects
• →Creating sound effects for games and videos
• →Experimenting with style transfers using audio-to-audio generation
• →Transforming vocals into music and sound effects