Added value: +"The generation, from generate_sound or get_generation"

Previous value: -"Recommended: SFXMint writes the prompt into the description the model gets, as the website's AI Enhance does, and the result gives that description. Default false: the prompt goes to the model exactly as written."New value: +"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."

Previous value: -"The sound the user needs, in plain words and any language: what it is for and what should be heard. With enhance (recommended), SFXMint writes the description the model gets. Leave out lengths (use duration_s)."New value: +"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."

Added value: +{
+  "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.",
+  "properties": {
+    "order_id": {
+      "type": "string"
+    },
+    "take": {
+      "description": "Which of its takes (1-4)",
+      "type": "number"
+    }
+  },
+  "required": [
+    "order_id",
+    "take"
+  ],
+  "type": "object"
+}

Previous value: -"Let SFXMint write the prompt into a full sound description first, as the website's AI Enhance does: a short idea ('coin', 'level complete'), another language, or words that leave something out. Default false: the prompt goes to the model exactly as written. The result gives the description it used."New value: +"Recommended: SFXMint writes the prompt into the description the model gets, as the website's AI Enhance does, and the result gives that description. Default false: the prompt goes to the model exactly as written."

Previous value: -"One sound, in plain English: what makes it, what it does and how it develops, e.g. 'a heavy wooden door slams shut and rattles in its frame' or 'three bright notes rise quickly, then a soft sparkle'. Name what is heard, not what it is for. Write only what should be heard: the model reads 'no thunder' as thunder. Leave out lengths (use duration_s) and 'sound effect'; add a place (large hall, distant, outdoors) when it matters. For a one- or two-word idea, another language or words that exclude something, set enhance. The model's weak spots: small ringing things written as one dense mass: a burst, shower, spill, pile or overlapping rush of coins, bells, ice, glass or gems: the rings blur into a hiss with no clear tone; write for a game reward (coins, gems, loot), a quick rising jingle of bright dings; for real things, separate hits you could count, each with its ring (four ice cubes dropping into a glass one at a time, each a clear clink). the ambience of a busy indoor public place: a train or metro station, an airport hall, a shopping mall: a muddy rumble or a noisy wash with nothing recognisable in it; write the place by one steady source with few events, the way a plane cabin, an office or a fireplace ambience is written. clear spoken words, lyrics, a song or a music track: a voice with indistinct words, or a short musical sound rather than a track; write a voice whose words are indistinct, or the closest short sound (a chord, a sting, a drum hit) with no key, tempo or other song terms. a seamless loop, or a sound that keeps going without an end: one sound with a start and an end, not a loop; write the sound as one take of the longest length, without loop words."New value: +"The sound the user needs, in plain words and any language: what it is for and what should be heard. With enhance (recommended), SFXMint writes the description the model gets. Leave out lengths (use duration_s)."

Previous value: -"One sound, in plain English: what makes it, what it does and how it develops, e.g. 'a heavy wooden door slams shut and rattles in its frame' or 'three bright notes rise quickly, then a soft sparkle'. Name what is heard, not what it is for. Write only what should be heard: the model reads 'no thunder' as thunder. Leave out lengths (use duration_s) and 'sound effect'; add a place (large hall, distant, outdoors) when it matters. For a one- or two-word idea, another language or words that exclude something, set enhance. The model's weak spots: ${weakSpotGuide()}."New value: +"One sound, in plain English: what makes it, what it does and how it develops, e.g. 'a heavy wooden door slams shut and rattles in its frame' or 'three bright notes rise quickly, then a soft sparkle'. Name what is heard, not what it is for. Write only what should be heard: the model reads 'no thunder' as thunder. Leave out lengths (use duration_s) and 'sound effect'; add a place (large hall, distant, outdoors) when it matters. For a one- or two-word idea, another language or words that exclude something, set enhance. The model's weak spots: small ringing things written as one dense mass: a burst, shower, spill, pile or overlapping rush of coins, bells, ice, glass or gems: the rings blur into a hiss with no clear tone; write for a game reward (coins, gems, loot), a quick rising jingle of bright dings; for real things, separate hits you could count, each with its ring (four ice cubes dropping into a glass one at a time, each a clear clink). the ambience of a busy indoor public place: a train or metro station, an airport hall, a shopping mall: a muddy rumble or a noisy wash with nothing recognisable in it; write the place by one steady source with few events, the way a plane cabin, an office or a fireplace ambience is written. clear spoken words, lyrics, a song or a music track: a voice with indistinct words, or a short musical sound rather than a track; write a voice whose words are indistinct, or the closest short sound (a chord, a sting, a drum hit) with no key, tempo or other song terms. a seamless loop, or a sound that keeps going without an end: one sound with a start and an end, not a loop; write the sound as one take of the longest length, without loop words."

Previous value: -"One sound, in plain English: what makes it, what it does and how it develops, e.g. 'a heavy wooden door slams shut and rattles in its frame' or 'three bright notes rise quickly, then a soft sparkle'. Name what is heard, not what it is for. Write only what should be heard: the model reads 'no thunder' as thunder. Leave out lengths (use duration_s) and 'sound effect'; add a place (large hall, distant, outdoors) when it matters. For a one- or two-word idea, another language or words that exclude something, set enhance."New value: +"One sound, in plain English: what makes it, what it does and how it develops, e.g. 'a heavy wooden door slams shut and rattles in its frame' or 'three bright notes rise quickly, then a soft sparkle'. Name what is heard, not what it is for. Write only what should be heard: the model reads 'no thunder' as thunder. Leave out lengths (use duration_s) and 'sound effect'; add a place (large hall, distant, outdoors) when it matters. For a one- or two-word idea, another language or words that exclude something, set enhance. The model's weak spots: ${weakSpotGuide()}."

Previous value: -"How many takes to make (default 4; the price is the same)"New value: +"How many takes to make (default 4; one generation either way)"

Previous value: -"Let SFXMint rewrite a short or unclear idea ('coin', 'level complete') into a full sound description first; a clear description still goes as written (default false: the prompt is used as written). The result gives the rewrite it used, if any."New value: +"Let SFXMint write the prompt into a full sound description first, as the website's AI Enhance does: a short idea ('coin', 'level complete'), another language, or words that leave something out. Default false: the prompt goes to the model exactly as written. The result gives the description it used."

Previous value: -"One sound, in English: a short noun phrase that ends with the sound itself, e.g. 'heavy wooden door slam' or 'bright rising three-note chime'. Name what is heard, not what it is for; leave out no/not/without, lengths (use duration_s) and 'sound effect'. Add a place (large hall, distant, outdoors) only when it matters. For a one- or two-word idea, set enhance."New value: +"One sound, in plain English: what makes it, what it does and how it develops, e.g. 'a heavy wooden door slams shut and rattles in its frame' or 'three bright notes rise quickly, then a soft sparkle'. Name what is heard, not what it is for. Write only what should be heard: the model reads 'no thunder' as thunder. Leave out lengths (use duration_s) and 'sound effect'; add a place (large hall, distant, outdoors) when it matters. For a one- or two-word idea, another language or words that exclude something, set enhance."