Stable Audio
Stable Audio is Stability AI’s music and sound effect generator, built on the Stable Audio 3.0 model family trained on licensed data, with DAW integration.
About this tool
Stable Audio is the audio generation product from Stability AI. It creates music and sound effects from conversational prompts, and supports editing existing audio through audio-to-audio transformation and inpainting. Tracks can range from short loops to compositions of about six minutes, and experimental stem export separates generated parts.
It is built on Stable Audio 3.0, a model family that Stability AI says was trained on fully licensed data and is also offered to developers as a foundation for their own audio tools. Producers can use it inside major digital audio workstations such as Ableton, Logic and Pro Tools, build sample libraries and integrate it into apps. Billing is per generation.
What you can do
Prompt-based generation
Create music and sound effects by describing them in conversation.
Audio-to-audio and inpainting
Transform or fill parts of existing audio to iterate on ideas.
DAW integration
Use Stable Audio inside Ableton, Logic, Pro Tools and other DAWs.
Licensed training data
Stable Audio 3.0 is described as trained on fully licensed data.
Who is it for?
- A producer generates song starters and sample packs without leaving the DAW.
- A sound designer creates effects for a mobile game.
- A developer integrates audio generation into a creative app.
Before you choose
Pay-per-generation pricing rewards planning; iterating many times increases cost.
Stem export is experimental, so separated parts may need cleanup.
Frequently asked questions
Who makes Stable Audio?
Stable Audio is developed by Stability AI, the company known for the Stable Diffusion image models.
Can Stable Audio run in my DAW?
Yes. Stability AI says Stable Audio 3.0 can be used inside common DAWs such as Logic, Pro Tools and Ableton.
What data was Stable Audio trained on?
Stability AI states that the Stable Audio 3.0 model family is trained on fully licensed data.
Check the official website for current features, pricing, and terms.
Similar tools
Stability AI
Image & DesignStability AI develops the Stable Diffusion image models and Stable Audio, offered through an API, open weights and enterprise solutions.
Suno
AudioSuno is an audio‑creation platform that lets creators and producers generate songs from lyrics, transform text into spoken audio, and design custom sound effects.
SOUNDRAW
AudioSOUNDRAW is an AI music and beat generator trained only on music made in-house, producing royalty-free tracks you can customise with a mixer.
AIVA
AudioAIVA is an AI music generation assistant that composes tracks in more than 250 styles, with editing tools and a Pro plan that grants full copyright ownership.
WarpSound
AudioWarpSound combines AI music generation with interactive playback, allowing users to create original compositions from simple inputs.
Udio
AudioUdio generates songs from text descriptions and offers tools to edit music, lyrics and voices, extend uploaded audio and publish tracks to a community.