Stable Audio

Overview

Stable Audio is an AI music creation platform from Stability AI. Using text-to-audio and audio-to-audio generation, users simply enter a text description or upload audio material to produce music that fits their needs. The platform can generate audio up to three minutes long in 44.1kHz stereo. Music created with Stable Audio is cleared for commercial use. It is well suited for music creators, producers, and everyday users who want to explore music creation.

Core capabilities

Text-to-Audio

Generate music by entering detailed text descriptions such as style, instruments, mood, and BPM.

Audio-to-Audio

Upload audio files and use text descriptions to apply style transfer or create variations.

Multiple model options

Choose from various audio generation model versions to match your needs.

Detailed prompt structure

Optimize output with structured prompts for format, style, instruments, mood, BPM, and more.

Advanced settings

Adjust parameters like input strength, step count, and seed value to control audio quality and diversity.

Use cases

Generate background music and sound effects for short videos

Create ambient music and transition sound effects for game levels

Produce opening, closing, and interstitial music for podcasts

Generate custom scores for advertising videos

Quickly create temp tracks for short films

Generate ambient sounds and mood music for audiobooks

Add unique sound effects to social media posts

Generate electronic or ambient music for live performances

Create background music for educational video narration

Quickly produce demo music for personal projects