Skip to main content
idapt
HomeAI ModelsExploreResourcesPricing
Sign inUse for Free
Music Models
Stability AI logo

Stable Audio 2.5

by Stability AI

Music and sound effects from one prompt.

Stable Audio 2.5 renders instrumental music, ambience and effects up to two minutes, and takes a start-and-end inpainting prompt to rework a section. The flexible middle ground between a song model and a sound-effect model.

More details

Stable Audio 2.5 by Stability AI is a standard-speed AI music generation model. Stable Audio 2.5 renders instrumental music, ambience and effects up to two minutes, and takes a start-and-end inpainting prompt to rework a section. The flexible middle ground between a song model and a sound-effect model. It renders instrumental tracks, sound effects, clips of 10 seconds, 30 seconds, 60 seconds, 120 seconds, prompts up to 1,000 characters.

Stable Audio 2.5 is priced at $0.001 per second of generated audio, so the default 10-second clip costs $0.01 and the longest 120-second clip costs $0.13. Commercial use of the generated audio is allowed under the provider terms. You can generate music with Stable Audio 2.5 on idapt.app alongside 200+ AI models in one workspace.

Pricing

Cost per second

$0.001

Default clip (10s)

$0.01

Billed on the length of the rendered audio

Longest clip (120s): $0.13

Capabilities

Speed

Standard: A short track in under a minute

Output

instrumental · sound effects

Lyrics

Instrumental only

Lengths

10s · 30s · 60s · 120s

Max Prompt

1,000 characters

Commercial use

Allowed by the model provider

Generate music with Stable Audio 2.5View Details

Stable Audio 2.5 questions

Who makes Stable Audio 2.5?

Stable Audio 2.5 is made by Stability AI and is served on idapt through the Stability AI API.

How much does Stable Audio 2.5 cost?

$0.001 per second of generated audio. A 10-second clip costs about $0.01.

Does Stable Audio 2.5 produce vocals?

No. It renders instrumental audio only, with no sung or spoken voice.

How long can a Stable Audio 2.5 clip be?

Lengths are picked from a fixed set: 10 seconds, 30 seconds, 60 seconds, 120 seconds. The default is 10 seconds and the longest is 120 seconds.

Can I use Stable Audio 2.5 output commercially?

Yes. The provider terms allow commercial use of the generated audio.

What are the alternatives to Stable Audio 2.5?

idapt lists 12 music generation models. The most-used alternatives are MusicGen Stereo Large and MiniMax Music 2.6.

A 10-second clip on this model costs about $0.01.

  • Home
  • Pricing
  • AI Models
  • Skills
  • Image models
  • Voice models
  • Video models
  • Music models
  • Embedding models
  • Rankings
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Actions
  • AI Gateway
  • All features →
  • Blog
  • About
  • Comparisons
  • Benchmarks
  • Demos
  • Help center
  • FAQ
  • Privacy
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Migrate
  • Downloads
  • Desktop
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)Discord