Stable Audio 3 Small SFX (Text-to-Audio)
Stable Audio 3 Small SFX makes sound effects up to 2 minutes long from a text description: impacts, foley, ambience. A flat $0.0206 a clip.
Stable Audio 3 Small SFX is a 459-million-parameter text-to-sound-effects model from Stability AI, designed to run on a phone or a laptop, released in May 2026. Describe a sound and it makes it, from a second to 2 minutes: an impact, footsteps, a door, weather, a crowd or an ambience bed.
Say what the sound is in prompt, and what to keep out in negative_prompt. duration sets the length, 1 to 120 seconds (30 by default); seed repeats a result; num_inference_steps (1-100, 8 by default) rarely needs changing on this distilled model; output_format picks mp3 (the default, 192 kbit/s), wav, flac, ogg, opus, m4a or aac.
Inputs: prompt (required), negative_prompt, duration, seed, num_inference_steps and output_format. Outputs: audio (the sound) and seed.
Price: $0.0206 per audio at list, a flat price: the length does not change it. It makes one sound per request. It makes neither music with lyrics nor speech, and it does not add sound to a video.
- Sound Effects
Price: $0.0206 per run. One run with default settings costs $0.0206.
Run Stable Audio 3 Small SFX (Text-to-Audio) via API
curl -X POST https://api.flymy.ai/api/v1/flymyai/stable-audio-3-small-sfx-text-to-audio/predict \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A single knock on a wooden door","duration":3}'API documentation · Create a free account · Pricing