{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/SpeechToSpeechRequest",
  "title": "SpeechToSpeechRequest",
  "type": "object",
  "required": [
    "audio"
  ],
  "properties": {
    "audio": {
      "type": "string",
      "format": "binary",
      "description": "The source audio file containing the speech to convert. Supports common audio formats including MP3, WAV, and OGG."
    },
    "model_id": {
      "type": "string",
      "description": "The identifier of the model to use for voice conversion."
    },
    "voice_settings": {
      "type": "object",
      "description": "Voice settings to override the default settings for the target voice.",
      "properties": {
        "stability": {
          "type": "number",
          "description": "Controls the stability of the converted voice output.",
          "minimum": 0,
          "maximum": 1
        },
        "similarity_boost": {
          "type": "number",
          "description": "Controls how closely the output matches the target voice.",
          "minimum": 0,
          "maximum": 1
        },
        "style": {
          "type": "number",
          "description": "Controls the expressiveness of the converted speech.",
          "minimum": 0,
          "maximum": 1
        },
        "use_speaker_boost": {
          "type": "boolean",
          "description": "Enables speaker boost for increased clarity."
        }
      }
    },
    "seed": {
      "type": "integer",
      "description": "A seed value for deterministic generation."
    }
  }
}