{"version":"1","model":{"id":"fal-ai/stable-audio-3/medium/text-to-audio","name":"Stable Audio 3","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"Generate high-quality stereo music and audio up to 380 seconds from text prompts using Stability AI's Stable Audio 3 Medium — trained on licensed data for commercial use.","pricing_note":"~$0.04 / generation (any duration)","categories":["music","sfx"],"prompt_required":true,"prompt_supported":true,"supports":{},"aspect_ratios":[],"resolutions":[],"durations":[],"base_credits":5,"api_gross_margin_percent":20,"added_at":"2026-07-02","popularity_rank":26,"example_prompt":"A slow cinematic orchestral swell — strings building from pianissimo to fortissimo, low brass entering at the climax, kettle drums rolling in the background","preview":{"image":"/images/model-previews/generated/stable-audio-3-text-to-audio-v1.webp"},"schema_url":"/api/v1/models?id=fal-ai%2Fstable-audio-3%2Fmedium%2Ftext-to-audio","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fstable-audio-3%2Fmedium%2Ftext-to-audio","title":"Stable Audio 3 generation request","description":"Request body accepted by POST /api/v1/generate for fal-ai/stable-audio-3/medium/text-to-audio.","type":"object","properties":{"model_id":{"type":"string","const":"fal-ai/stable-audio-3/medium/text-to-audio","description":"ArtEmotion model identifier."},"extra":{"type":"object","additionalProperties":true,"description":"Model-specific settings may also be nested here."},"max_credits":{"type":"number","minimum":1,"description":"Reject before submission if the estimated list price exceeds this cap."},"webhook_url":{"type":"string","format":"uri","maxLength":2048},"webhook_secret":{"type":"string","maxLength":512},"folder_id":{"type":"string"},"prompt":{"type":"string"},"duration":{"title":"Duration (s)","description":"Duration of the generated audio in seconds (1–380).","default":30,"type":"number","minimum":1,"maximum":380,"multipleOf":1},"output_format":{"title":"Output Format","description":"Audio container/codec for the output file.","default":"mp3","type":"string","enum":["mp3","wav","flac","ogg","opus","m4a","aac"]},"bitrate":{"title":"Bitrate","description":"Bitrate for compressed output formats.","default":"192k","type":"string","enum":["192k","320k"]},"negative_prompt":{"title":"Negative Prompt","description":"Describe what the audio should avoid.","default":"","type":"string"},"num_inference_steps":{"title":"Inference Steps","description":"Number of diffusion steps. Higher = slightly better quality, slower.","default":8,"type":"number","minimum":1,"maximum":100,"multipleOf":1},"guidance_scale":{"title":"Guidance Scale","description":"How closely the model follows the prompt. Higher = more literal.","default":1,"type":"number","minimum":0,"maximum":25,"multipleOf":0.5},"seed":{"title":"Seed","description":"Set a seed for reproducible results. Leave blank for random.","type":"integer"},"enable_prompt_expansion":{"title":"Prompt Expansion","description":"Let the model expand short prompts into richer descriptions.","default":false,"type":"boolean"},"enable_safety_checker":{"title":"Safety Checker","description":"Screen the output for unsafe content.","default":true,"type":"boolean"}},"required":["model_id","prompt"],"additionalProperties":false},"parameters":[{"key":"duration","label":"Duration (s)","type":"number","default":30,"min":1,"max":380,"step":1,"description":"Duration of the generated audio in seconds (1–380)."},{"key":"output_format","label":"Output Format","type":"select","default":"mp3","options":["mp3","wav","flac","ogg","opus","m4a","aac"],"description":"Audio container/codec for the output file."},{"key":"bitrate","label":"Bitrate","type":"select","default":"192k","options":["192k","320k"],"description":"Bitrate for compressed output formats."},{"key":"negative_prompt","label":"Negative Prompt","type":"text","default":"","description":"Describe what the audio should avoid."},{"key":"num_inference_steps","label":"Inference Steps","type":"number","default":8,"min":1,"max":100,"step":1,"description":"Number of diffusion steps. Higher = slightly better quality, slower."},{"key":"guidance_scale","label":"Guidance Scale","type":"number","default":1,"min":0,"max":25,"step":0.5,"description":"How closely the model follows the prompt. Higher = more literal."},{"key":"seed","label":"Seed","type":"seed","description":"Set a seed for reproducible results. Leave blank for random."},{"key":"enable_prompt_expansion","label":"Prompt Expansion","type":"toggle","default":false,"description":"Let the model expand short prompts into richer descriptions."},{"key":"enable_safety_checker","label":"Safety Checker","type":"toggle","default":true,"description":"Screen the output for unsafe content."}]}}