Stable Audio 3

{
  "model_id": "fal-ai/stable-audio-3/medium/text-to-audio",
  "prompt": "A slow cinematic orchestral swell — strings building from pianissimo to fortissimo, low brass entering at the climax, kettle drums rolling in the background"
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$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
}