MiniMax Speech-02 HD

{
  "model_id": "fal-ai/minimax/speech-02-hd",
  "prompt": "Welcome to the MiniMax Speech demo. Today we're exploring high-definition voice synthesis — expressive, natural, and multilingual. Let's hear what modern TTS can really do."
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fminimax%2Fspeech-02-hd",
  "title": "MiniMax Speech-02 HD generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/minimax/speech-02-hd.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/minimax/speech-02-hd",
      "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"
    },
    "voice_id": {
      "title": "Voice",
      "description": "MiniMax pre-trained voice persona.",
      "default": "Wise_Woman",
      "type": "string",
      "enum": [
        "Abbess",
        "Calm_Woman",
        "Casual_Guy",
        "Decent_Boy",
        "Deep_Voice_Man",
        "Determined_Man",
        "Elegant_Man",
        "Exuberant_Girl",
        "Friendly_Person",
        "Imposing_Manner",
        "Inspirational_girl",
        "Lively_Girl",
        "Lovely_Girl",
        "Patient_Man",
        "Sweet_Girl_2",
        "Wise_Woman",
        "Young_Knight"
      ]
    },
    "language_boost": {
      "title": "Language Boost",
      "description": "Boosts recognition accuracy for the selected language. Use Auto for mixed-language text.",
      "default": "auto",
      "type": "string",
      "enum": [
        "auto",
        "English",
        "Chinese",
        "Chinese,Yue",
        "Japanese",
        "Korean",
        "Spanish",
        "French",
        "German",
        "Portuguese",
        "Arabic",
        "Hindi",
        "Russian",
        "Dutch",
        "Turkish",
        "Italian",
        "Polish",
        "Swedish",
        "Ukrainian",
        "Vietnamese",
        "Indonesian",
        "Thai",
        "Romanian",
        "Greek",
        "Czech",
        "Finnish",
        "Danish",
        "Hebrew",
        "Malay",
        "Slovak",
        "Croatian",
        "Hungarian",
        "Norwegian",
        "Bulgarian",
        "Slovenian",
        "Catalan",
        "Afrikaans",
        "Nynorsk"
      ]
    },
    "speed": {
      "title": "Speed",
      "description": "Speech speed multiplier (0.5–2.0).",
      "default": 1,
      "type": "number",
      "minimum": 0.5,
      "maximum": 2,
      "multipleOf": 0.05
    },
    "vol": {
      "title": "Volume",
      "description": "Output volume level (0.01–10). 1 is the default.",
      "default": 1,
      "type": "number",
      "minimum": 0.01,
      "maximum": 10,
      "multipleOf": 0.05
    },
    "pitch": {
      "title": "Pitch",
      "description": "Voice pitch shift in semitones (-12 to +12). 0 is unchanged.",
      "default": 0,
      "type": "number",
      "minimum": -12,
      "maximum": 12,
      "multipleOf": 1
    },
    "emotion": {
      "title": "Emotion",
      "description": "Emotional tone of the generated speech.",
      "default": "",
      "type": "string",
      "enum": [
        "",
        "happy",
        "sad",
        "angry",
        "fearful",
        "disgusted",
        "surprised",
        "neutral"
      ]
    },
    "english_normalization": {
      "title": "English Normalization",
      "description": "Improves number reading (e.g. dates, prices). Adds slight latency.",
      "default": false,
      "type": "boolean"
    },
    "output_format": {
      "title": "Output Format",
      "description": "Format of the output content (non-streaming only).",
      "default": "hex",
      "type": "string",
      "enum": [
        "url",
        "hex"
      ]
    },
    "tone_list": {
      "title": "Tone List",
      "description": "Pronunciation replacements in 'text/(pronunciation)' format. For Chinese, use tones 1–5.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "as_format": {
      "title": "Audio Format",
      "description": "Output audio encoding format.",
      "default": "mp3",
      "type": "string",
      "enum": [
        "mp3",
        "pcm",
        "flac"
      ]
    },
    "as_sample_rate": {
      "title": "Sample Rate",
      "description": "Sample rate of the generated audio in Hz.",
      "default": "32000",
      "type": "number",
      "enum": [
        8000,
        16000,
        22050,
        24000,
        32000,
        44100
      ]
    },
    "as_bitrate": {
      "title": "Bitrate",
      "description": "Audio bitrate in bits per second.",
      "default": "128000",
      "type": "number",
      "enum": [
        32000,
        64000,
        128000,
        256000
      ]
    },
    "as_channel": {
      "title": "Channels",
      "description": "Number of audio channels.",
      "default": "1",
      "type": "number",
      "enum": [
        1,
        2
      ]
    }
  },
  "required": [
    "model_id",
    "prompt"
  ],
  "additionalProperties": false
}