stability-ai/stable-audio-2.5 🔢📝 → 🖼️

⭐ Official ▶️ 3.0K runs 📅 Sep 2025 ⚙️ Cog 0.16.7 ⚖️ License

audio-to-audio music-generation sound-effect-generation

About

Generate high-quality music and sound from text prompts

Example Output

Prompt:

"Pop, Pop-Electronic, Ballad, Billboard, Drum Machine, Bass, Lush Synthesizer Pads, Synthesizer Arp, Synth Bass, Vocal Sample Chops, Percussion, Honest, Heart-Felt, Melancholic, Vibe, Cool, Modern, Atmospheric, well-arranged composition, 115 BPM"

Output

Performance Metrics

5.79s Prediction Time

5.80s Total Time

All Input Parameters

{
  "steps": 8,
  "prompt": "Pop, Pop-Electronic, Ballad, Billboard, Drum Machine, Bass, Lush Synthesizer Pads, Synthesizer Arp, Synth Bass, Vocal Sample Chops, Percussion, Honest, Heart-Felt, Melancholic, Vibe, Cool, Modern, Atmospheric, well-arranged composition, 115 BPM",
  "duration": 90,
  "cfg_scale": 1
}

Input Parameters

seed Type: integer: Random seed for reproducible results. Leave blank for random seed.
steps Type: integerDefault: 8Range: 4 - 8: Number of diffusion steps (higher = better quality but slower)
prompt (required) Type: string: Text prompt describing the desired audio
duration Type: integerDefault: 190Range: 1 - 190: Duration of generated audio in seconds
cfg_scale Type: numberDefault: 1Range: 1 - 25: Classifier-free guidance scale (higher = more prompt adherence)

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 1025718006
Generated audio in 5.8sec

Version Details

Version ID: a58cbacb1019d375b25d33fa3d9c2b5181486873b4819ce9d69b20fd444e0d97
Version Created: September 11, 2025

Run on Replicate →