S

Stable Audio

Generate music and sound from text

by Stability AI

Overview

Stable Audio is Stability AI's generative model for music and sound. From a text prompt it produces original instrumental tracks, loops and sound effects of controllable length, giving creators royalty-friendly audio for videos, games and other projects without licensing headaches.

Key Features

  • β€’Text-to-music generation
  • β€’Sound effect creation
  • β€’Controllable track length
  • β€’Audio-to-audio transformation
  • β€’Commercial-use licensing
  • β€’API access for developers

Use Cases

  • β†’Background music for videos
  • β†’Game and app sound effects
  • β†’Podcast and ad stingers
  • β†’Prototyping audio ideas

Pros

  • βœ“Original, license-friendly audio
  • βœ“Fast generation of loops and effects
  • βœ“Useful length control
  • βœ“Backed by Stability AI research

Cons

  • βœ•Not for realistic vocals or songs
  • βœ•Quality varies by genre
  • βœ•Best features are paid

Frequently Asked Questions

Is Stable Audio free?

It offers a free tier with limits; paid plans add more generations, length and commercial rights.

Can I use the audio commercially?

Yes, paid plans include commercial licensing for the audio you generate.

Does it generate vocals?

It focuses on instrumental music and sound effects rather than realistic sung vocals.

Is there an API?

Yes, Stability AI offers API access for integrating audio generation into apps.

Comments (66)

Log in to view and post comments

Upvote
Visit Website β†’

Basic Info

Pricing
Freemium
Launch Date
2023-09-13
Maker
Stability AI