Skip to main content
ModelSpeech & Audio AIvstable-audio-2.0

Stable Audio

by Stability AI · paid · Last verified 2026-03-17

Stability AI's latent diffusion model for generating high-quality music and sound effects from text descriptions. Produces variable-length stereo audio at 44.1kHz, suitable for commercial music production and sound design workflows.

https://stability.ai/stable-audio
C+
C+Average
Adoption: C+Quality: B+Freshness: ACitations: C+Engagement: F

Specifications

License
Proprietary
Pricing
paid
Capabilities
text-to-audio, music-generation, sound-effect-generation, stereo-output, variable-length
Integrations
stability-api
Use Cases
music-production, sound-design, game-audio, podcast-intros, advertising
API Available
Yes
Parameters
Undisclosed
Context Window
N/A
Modalities
text, audio
Training Cutoff
Mid 2024
Tags
audio-generation, music, text-to-audio, sound-design, creative
Added
2026-03-17
Completeness
95%

Index Score

50.1
Adoption
55
Quality
78
Freshness
80
Citations
50
Engagement
0

Explore the full AI ecosystem on Agents as a Service