Stable Audio 3 Medium2026ai_remix
AI Cover - Stable Audio 3 (Stable Audio 3 Medium)
Model card for the Stable Audio 3 Medium model behind the AI Cover - Stable Audio 3 preset in Neural Analog.
Available in Studio. Uses standard processing minutes.
Stable Audio 3 Medium Description
This instrumental music model generates an AI cover using the input audio as a reference. The settings let you make the result more or less similar to the original. Does not work with singing! Remix your instrumentals, turn noise into musical sounds, and repair low frequencies.
Stable Audio 3 Medium Architecture
Stable Audio 3 Medium Parameters
| Key | Label | Options | Description |
|---|---|---|---|
| model_name | Model variant | Stable Audio 3 Medium (stable-audio-3-medium) | No additional help text. |
| strength | Remix Strength | 0.01 - Minimal edit (0.01), 0.1 - Light edit (0.1), 0.3 - Bit more edit (0.3), 0.5 - Balanced edit (0.5), 0.6 - Moderate remix (0.6), 0.7 - Strong remix (0.7), 0.95 - Totally different song (0.95) | High values produce results very different from the input audio. Sometimes too different. |
| prompt | Prompt | Free text | Use keywords to describe the style you want. For example: *italian western, cinematic score, mellow strings and choir* |
| prompt_strength | Prompt Strength | 0.5 - Less prompt strength (0.5), 1 - Base prompt strength (1), 2 - More prompt (2), 3 - Stronger prompt (3), 4 - Even more prompt (4), 5 - High prompt strength (5), 6 - Very high prompt strength (6), 7 - Maximum prompt (7) | Increases the prompt's influence relative to the original music. High values produce the most creative and different results. |