Stable Audio 2
by Stability AI · freemium · Last verified 2026-03-17
Stable Audio 2 from Stability AI is a latent diffusion model capable of generating up to 3-minute stereo music and audio at 44.1kHz, making it the first publicly released model to produce near-CD-quality long-form audio generation. It supports precise timing and structure control through natural language, enabling users to specify song sections, BPM, and mood with high fidelity.
https://stability.ai/stable-audio ↗C+
C+—Average
Adoption: C+Quality: AFreshness: B+Citations: BEngagement: F
Specifications
- License
- Stability AI Non-Commercial Research Community License
- Pricing
- freemium
- Capabilities
- text-to-music, text-to-audio, long-form-audio, 44khz-stereo-output, timed-generation
- Integrations
- stability-api
- Use Cases
- music-production, game-audio, film-scoring, sound-design, content-soundtracking
- API Available
- Yes
- Parameters
- Undisclosed
- Context Window
- N/A
- Modalities
- text, audio
- Training Cutoff
- 2024
- Tags
- music-generation, audio-generation, text-to-audio, stability-ai, diffusion
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
54.5Adoption
55
Quality
85
Freshness
78
Citations
62
Engagement
0