Sounds

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "With enhance=false, describe the audible environment in plain English, at most 400 characters. Name the place and continuous sound bed, its intensity, texture and pace; include occasional events, their spacing and distance only when requested or established by context. Keep it steady and repeatable. Example: 'Gentle ocean waves wash onto a sandy beach and recede at a steady pace, with soft foamy hiss and a low rolling wash.' Preserve the user's sources and spatial details; omit excluded sounds entirely rather than listing 'no music' or 'without voices'. Avoid metaphors that introduce other sources. The server adds the SFX tag and continuous-ambience instruction. With enhance=true, a brief in any language is enough."
    },
    "enhance": {
      "type": "boolean",
      "description": "Default false. Write final English using this tool's prompt guidance to skip server AI rewriting. True asks the corresponding ambience or music writer to adapt a brief in any language; enhanced_prompt reports the result. Non-Latin input may still require server translation with false."
    },
    "duration_s": {
      "enum": [
        30
      ],
      "type": "number",
      "description": "Take length, fixed at 30 seconds; omit or pass 30. A returned loop may be shorter. A loop is not guaranteed: inspect loop_cut and loop_url."
    },
    "variations": {
      "enum": [
        1,
        2,
        4
      ],
      "type": "number",
      "description": "How many takes to make (default 4; one generation either way)"
    }
  }
}

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "With enhance=false, write a plain English instrumental music description, at most 400 characters, usually 1-3 sentences. State the genre, instruments and what they play, mood, energy and tempo (BPM if specified). Preserve named genres, instruments and pace; choose compatible instrumentation only when the brief leaves it open. Describe a repeating motif and steady accompaniment suitable for a background loop. Example: 'A calm fantasy instrumental loop at 80 BPM, with gentle harp arpeggios, warm sustained strings and a simple flute melody, keeping a steady, hopeful mood.' Use positive audible terms; omit unwanted sources instead of naming them in exclusions. Avoid artist, song or game names, lyrics and the 'TrackType: SFX' tag. With enhance=true, give the musical brief in any language and the music writer adapts it."
    },
    "enhance": {
      "type": "boolean",
      "description": "Default false. Write final English using this tool's prompt guidance to skip server AI rewriting. True asks the corresponding ambience or music writer to adapt a brief in any language; enhanced_prompt reports the result. Non-Latin input may still require server translation with false."
    },
    "duration_s": {
      "enum": [
        30
      ],
      "type": "number",
      "description": "Take length, fixed at 30 seconds; omit or pass 30. A returned loop may be shorter. A loop is not guaranteed: inspect loop_cut and loop_url."
    },
    "variations": {
      "enum": [
        1,
        2,
        4
      ],
      "type": "number",
      "description": "How many takes to make (default 4; one generation either way)"
    }
  }
}

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "For enhance=false, write the final audible description in plain English, usually 1-3 sentences, at most 400 characters. Start with 'TrackType: SFX,'. Name the source, action and relevant material; preserve requested count, intensity, pace and how the sound starts, develops and ends. Translate a use such as 'success' into the intended audible event, e.g. 'TrackType: SFX, three bright electronic tones rise in pitch, each fading quickly.' Preserve an explicitly requested sound: a confirmation click stays a click. Mention only sounds to be heard; omit excluded sounds entirely instead of writing 'no music' or 'without speech'. Avoid brands, character names and metaphors that name unwanted sources. Add perspective, environment or timbre only when requested or established by context; do not invent extra events. Keep simple sounds short. Put total length in duration_s. For enhance=true, a plain-language brief in any language is enough; SFXMint writes the model description."
    },
    "enhance": {
      "type": "boolean",
      "description": "Default false. Prefer false when you can write the final English sound description using the prompt guidance: it skips the server AI rewrite. True asks SFXMint to expand or adapt a brief, as the website's AI Enhance does; the result includes enhanced_prompt. With false, non-Latin text may still trigger server translation, so write English to avoid that extra call. Neither setting guarantees audio quality; listen to the takes."
    },
    "duration_s": {
      "enum": [
        0.2,
        0.5,
        1,
        1.5,
        2,
        2.5,
        3,
        4,
        5,
        6,
        7,
        8,
        9,
        10
      ],
      "type": "number",
      "description": "Longest length in seconds. Leave it out and SFXMint chooses from the description; either way the silence before and after the sound is cut, so a take can be shorter"
    },
    "variations": {
      "enum": [
        1,
        2,
        4
      ],
      "type": "number",
      "description": "How many takes to make (default 4; one generation either way)"
    },
    "variations_of": {
      "type": "object",
      "required": [
        "order_id",
        "take"
      ],
      "properties": {
        "take": {
          "type": "number",
          "description": "Which of its takes (1-4)"
        },
        "order_id": {
          "type": "string"
        }
      },
      "description": "A variation set instead of a new sound: four takes started from one finished take of this account's generation, close to it, for a game to play at random so the sound does not repeat (footsteps, hits, shots). The result adds engine files (a Godot AudioStreamRandomizer .tres and a Unity script) to save beside the WAVs. Uses one generation; prompt then only names the set."
    }
  }
}

{
  "type": "object",
  "required": [
    "role"
  ],
  "properties": {
    "loop": {
      "type": "boolean",
      "description": "Require prepared loop metadata; seam evidence is returned separately."
    },
    "role": {
      "type": "string",
      "description": "Role id or alias, e.g. 'click', 'button click', 'purchase-success', 'ka-ching', 'error beep', 'level-up', 'dialogue blip', 'notification'"
    },
    "style": {
      "enum": [
        "balanced",
        "crisp",
        "soft",
        "spacious"
      ],
      "type": "string",
      "description": "Optional. balanced (default) = the family's most typical take; crisp = short, bright, dry; soft = darker, gentler; spacious = reverb, longer tail"
    },
    "format": {
      "enum": [
        "wav",
        "mp3",
        "ogg"
      ],
      "type": "string"
    },
    "max_duration_ms": {
      "type": "number",
      "description": "Hard maximum delivered duration in milliseconds."
    }
  }
}

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "loop": {
      "type": "boolean",
      "description": "Require (true) or exclude (false) a candidate marked with prepared loop metadata; seam evidence is returned separately."
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 20, max 50)"
    },
    "query": {
      "type": "string",
      "description": "Use concise English search terms for the source or event, action and essential audible traits from the user's request or project context: 'door slam', 'soft UI confirmation chime', 'coin pickup'. A single clear source such as 'thunder' is valid; do not pad it. Translate other languages while preserving meaning. Avoid full generation prompts, app backstory, synonym lists and invented materials or environments: full matches must cover every query word. Put duration, loop and format requirements in their separate fields. If no full match exists, inspect closest and missing_terms; simplify only optional wording, never silently drop a required trait."
    },
    "format": {
      "enum": [
        "wav",
        "mp3",
        "ogg"
      ],
      "type": "string",
      "description": "Delivery format (ogg = Ogg Vorbis, only sounds published before 2026-10-14 have it); loop=true defaults to WAV when omitted."
    },
    "category": {
      "type": "string",
      "description": "Optional category slug: ui, retro-game, transition, impact, ambience, water, fire-electric, footsteps, door, mechanical, paper-fabric, glass, animal, crowd, cartoon, magic-scifi, horror, feedback, instrument, office, human, vehicle, household"
    },
    "max_duration_ms": {
      "type": "number",
      "description": "Hard maximum delivered duration in milliseconds; format-specific measurement is required."
    }
  }
}