fal-ai/stable-audio-3/medium/audio-inpainting
Stable Audio 3 Medium audio inpainting is a 1.4 billion parameter latent diffusion model that fills in or reworks selected segments of a stereo track guided by text prompts, supporting single- and multi-segment editing.
Inference
Commercial use
Prompt examples
Examples are generated using the Stable Audio 3 Medium Audio Inpainting. You can customize them by clicking on the "Playground" button.
Fill only the silent gap with rainy rooftop future-soul instrumental with muted trumpet stabs, soft Rhodes chords, and crisp rim clicks; create a musical phrase that lands on the surrounding beat and keeps the key coherent. No vocals.
num_inference_steps8
guidance_scale1
seed730102
Regenerate the masked region as a polished song section that keeps the same emotional direction. Make the result feel soft, focused, and naturally mixed. Give it a fresh city view feeling.
num_inference_steps12
guidance_scale1
Fill only the silent gap with rainy rooftop future-soul instrumental with muted trumpet stabs, soft Rhodes chords, and crisp rim clicks; create a musical phrase that lands on the surrounding beat and keeps the key coherent. No vocals.
num_inference_steps8
guidance_scale1
seed730102