> ## Documentation Index
> Fetch the complete documentation index at: https://typecast.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Subscription

> Retrieve the authenticated user's current subscription information, including plan name, credit usage, concurrency limit, and custom voice slot capacity.

Use this endpoint to check remaining credits, verify your current plan, or see how many custom voice slots are available before cloning a new voice with `POST /v1/voices/clone`. The `limits.custom_voice_slot` value is the maximum number of custom voices the current plan can hold at once; free the slot by calling `DELETE /v1/voices/{voice_id}`.

## OpenAPI

```json
{
  "openapi": "3.1.0",
  "info": {
    "title": "Typecast API",
    "x-logo": {
      "url": "https://typecast.ai/_ipx/_/image/logo/tc_logo.webp"
    },
    "version": "0.1.2"
  },
  "servers": [
    {
      "url": "https://api.typecast.ai",
      "description": "Production server"
    }
  ],
  "security": [
    {
      "ApiKeyAuth": []
    }
  ],
  "paths": {
    "/v1/users/me/subscription": {
      "get": {
        "tags": [
          "Subscription"
        ],
        "x-mint": {
          "href": "/api-reference/subscription/get-subscription"
        },
        "summary": "Get Subscription",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/SubscriptionResponse"
                },
                "example": {
                  "plan": "lite",
                  "limits": {
                    "concurrency_limit": 5,
                    "custom_voice_slot": 10
                  },
                  "credits": {
                    "plan_credits": 200000,
                    "used_credits": 157300
                  }
                }
              }
            },
            "description": "Successful Response"
          },
          "401": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "detail": "Invalid API key"
                }
              }
            },
            "description": "Unauthorized - Authentication failed"
          },
          "429": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "detail": "Too many requests"
                }
              }
            },
            "description": "Too Many Requests - Rate limit exceeded"
          },
          "500": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "detail": "An unexpected error occurred"
                }
              }
            },
            "description": "Internal Server Error"
          }
        },
        "description": "Retrieve the authenticated user's current subscription information, including plan name, credit usage, concurrency limit, and custom voice slot capacity.\n\nUse this endpoint to check remaining credits, verify your current plan, or see how many custom voice slots are available before cloning a new voice with `POST /v1/voices/clone`. The `limits.custom_voice_slot` value is the maximum number of custom voices the current plan can hold at once; free the slot by calling `DELETE /v1/voices/{voice_id}`.",
        "operationId": "get_my_subscription_v1_users_me_subscription_get"
      }
    }
  },
  "components": {
    "schemas": {
      "Limits": {
        "type": "object",
        "title": "Limits",
        "required": [
          "concurrency_limit"
        ],
        "properties": {
          "concurrency_limit": {
            "type": "integer",
            "title": "Concurrency Limit",
            "description": "Maximum number of concurrent requests allowed"
          },
          "custom_voice_slot": {
            "type": "integer",
            "title": "Custom Voice Slot",
            "default": 0,
            "minimum": 0,
            "description": "Maximum number of custom voices (created via instant cloning) allowed on the current plan."
          },
          "professional_voice_slot": {
            "type": "integer",
            "title": "Professional Voice Slot",
            "default": 0,
            "minimum": 0,
            "description": "프리미엄 클로닝 보이스 슬롯 한도"
          }
        },
        "description": "Usage limit information"
      },
      "Prompt": {
        "title": "Prompt (ssfm-v21)",
        "properties": {
          "emotion_preset": {
            "example": "normal",
            "description": "Emotion preset to apply.\r\n\r\nSupported emotions for ssfm-v21: normal, happy, sad, angry\r\n\r\nCheck available emotions for each voice in the `models` field of the `GET /v3/voices` API response.\r\n"
          },
          "emotion_intensity": {
            "example": 1,
            "description": "Controls the strength of emotional expression (0.0 to 2.0).\r\n\r\n- 0.0: Completely neutral\r\n- 1.0: Standard expression (default)\r\n- 2.0: Maximum intensity\r\n"
          }
        },
        "description": "Emotion and style settings for the generated speech."
      },
      "AgeEnum": {
        "enum": [
          "child",
          "teenager",
          "young_adult",
          "middle_age",
          "elder"
        ],
        "type": "string",
        "title": "AgeEnum",
        "description": "Age group classification enum - Converts database values (Korean) to API values (English).\n\nAvailable values:\n- **child**: Child voice (under 12 years old)\n- **teenager**: Teenage voice (13-19 years old)\n- **young_adult**: Young adult voice (20-35 years old)\n- **middle_age**: Middle-aged voice (36-60 years old)\n- **elder**: Elder voice (over 60 years old)\n"
      },
      "Credits": {
        "type": "object",
        "title": "Credits",
        "required": [
          "plan_credits",
          "used_credits"
        ],
        "properties": {
          "plan_credits": {
            "type": "integer",
            "title": "Plan Credits",
            "description": "Total monthly credits provided by the plan"
          },
          "used_credits": {
            "type": "integer",
            "title": "Used Credits",
            "description": "Number of credits used"
          }
        },
        "description": "Credit usage information"
      },
      "VoiceV2": {
        "type": "object",
        "title": "VoiceV2",
        "required": [
          "voice_id",
          "voice_name",
          "models",
          "voice_type"
        ],
        "properties": {
          "age": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/AgeEnum"
              },
              {
                "type": "null"
              }
            ],
            "description": "Voice age group classification (child/teenager/young_adult/middle_age/elder)"
          },
          "gender": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/GenderEnum"
              },
              {
                "type": "null"
              }
            ],
            "description": "Voice gender classification (male/female)"
          },
          "models": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ModelInfo"
            },
            "title": "Models",
            "description": "List of supported TTS models with their available emotions (e.g., [{'version': 'ssfm-v21', 'emotions': ['happy', 'sad']}])"
          },
          "voice_id": {
            "type": "string",
            "title": "Voice Id",
            "description": "Unique voice identifier. Built-in voices use the `tc_` prefix (e.g., `tc_60e5426de8b95f1d3000d7b5`); cloned custom voices created via `POST /v1/voices/clone` use the `uc_` prefix. Use `/v3/voices` to list the built-in and completed custom voices available to your account."
          },
          "use_cases": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "title": "Use Cases",
            "description": "List of use case categories this voice is suitable for"
          },
          "voice_name": {
            "type": "string",
            "title": "Voice Name",
            "description": "Human-readable name of the voice"
          },
          "voice_type": {
            "$ref": "#/components/schemas/VoiceType",
            "description": "Voice type — `original` for Typecast-provided stock voices, `custom` for user-cloned voices."
          }
        },
        "description": "V2 Voice response model with model-grouped emotions and enhanced metadata"
      },
      "VoiceV3": {
        "type": "object",
        "title": "VoiceV3",
        "required": [
          "voice_id",
          "voice_name",
          "voice_type",
          "models"
        ],
        "properties": {
          "age": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/AgeEnum"
              },
              {
                "type": "null"
              }
            ],
            "description": "Voice age group."
          },
          "gender": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/GenderEnum"
              },
              {
                "type": "null"
              }
            ],
            "description": "Voice gender (`male` or `female`)."
          },
          "models": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ModelInfo"
            },
            "title": "Models",
            "description": "Supported TTS models and their available emotions."
          },
          "voice_id": {
            "type": "string",
            "title": "Voice Id",
            "description": "Unique voice identifier. Built-in voices use the `tc_` prefix and custom voices use the `uc_` prefix."
          },
          "use_cases": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "title": "Use Cases",
            "description": "Recommended use-case categories."
          },
          "voice_name": {
            "$ref": "#/components/schemas/VoiceName",
            "description": "Localized voice names, such as `{\"eng\": \"Daejin\", \"kor\": \"대진\"}`."
          },
          "voice_type": {
            "$ref": "#/components/schemas/VoiceType",
            "description": "Voice type (`original` or `custom`)."
          },
          "preview_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Preview Url",
            "description": "Preview audio URL when available."
          }
        },
        "description": "Voice metadata with localized names and a preview audio URL."
      },
      "PlanTier": {
        "enum": [
          "free",
          "lite",
          "plus",
          "custom"
        ],
        "type": "string",
        "title": "PlanTier",
        "description": "Subscription plan for the API.\n\nAvailable values:\n- **free**: Free tier with limited credits\n- **lite**: Lite plan with moderate credits\n- **plus**: Plus plan with higher credits\n- **custom**: Custom enterprise plan"
      },
      "TTSModel": {
        "enum": [
          "ssfm-v30",
          "ssfm-v21"
        ],
        "type": "string",
        "title": "TTSModel",
        "description": "TTS model version to use for speech synthesis. Different models offer varying capabilities and quality levels.\n\nAvailable models:\n- **ssfm-v30**: Latest model with improved prosody and additional emotion presets (recommended)\n- **ssfm-v21**: Stable production model with proven reliability and consistent quality\n"
      },
      "ModelInfo": {
        "type": "object",
        "title": "ModelInfo",
        "required": [
          "version",
          "emotions"
        ],
        "properties": {
          "version": {
            "$ref": "#/components/schemas/TTSModel",
            "description": "TTS model version (e.g., ssfm-v21, ssfm-v30)"
          },
          "emotions": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "title": "Emotions",
            "description": "List of supported emotions for this model"
          }
        },
        "description": "Model information including version and supported emotions"
      },
      "VoiceName": {
        "type": "object",
        "title": "VoiceName",
        "required": [
          "eng",
          "kor"
        ],
        "properties": {
          "eng": {
            "type": "string",
            "title": "Eng",
            "description": "English voice name."
          },
          "kor": {
            "type": "string",
            "title": "Kor",
            "description": "Korean voice name."
          }
        },
        "description": "Localized voice names keyed by ISO 639-3 language code."
      },
      "VoiceType": {
        "enum": [
          "original",
          "custom"
        ],
        "type": "string",
        "title": "VoiceType",
        "description": "Voice type classification.\n\n- `original` — Typecast-provided stock voices available to every account.\n- `custom` — Voices the user created by uploading or cloning their own sample."
      },
      "GenderEnum": {
        "enum": [
          "male",
          "female"
        ],
        "type": "string",
        "title": "GenderEnum",
        "description": "Gender classification enum - Converts database values (Korean) to API values (English).\n\nAvailable values:\n- **male**: Male voice\n- **female**: Female voice\n"
      },
      "EmotionEnum": {
        "enum": [
          "normal",
          "sad",
          "happy",
          "angry",
          "whisper",
          "toneup",
          "tonedown"
        ],
        "type": "string",
        "title": "EmotionEnum",
        "description": "Available emotion presets for speech synthesis. Each emotion affects the tone, pace, and expressiveness of the generated speech.\n\n**ssfm-v21 Supported Emotions (4 types):**\n- normal: Neutral, balanced tone\n- happy: Bright, cheerful expression\n- sad: Melancholic, subdued tone\n- angry: Strong, intense delivery\n\n**ssfm-v30 Supported Emotions (7 types):**\n- normal: Neutral, balanced tone\n- happy: Bright, cheerful expression\n- sad: Melancholic, subdued tone\n- angry: Strong, intense delivery\n- whisper: Soft, quiet speech\n- toneup: Higher tonal emphasis\n- tonedown: Lower tonal emphasis\n\nCheck available emotions for each voice in the `models` field of the `GET /v3/voices` API response.\n"
      },
      "SmartPrompt": {
        "type": "object",
        "title": "SmartPrompt (ssfm-v30)",
        "example": {
          "next_text": "I am literally bursting with happiness and I never want this feeling to end!",
          "emotion_type": "smart",
          "previous_text": "I feel like I'm walking on air and I just want to scream with joy!"
        },
        "properties": {
          "next_text": {
            "type": "string",
            "title": "Next Text",
            "default": "",
            "example": "I am literally bursting with happiness and I never want this feeling to end!",
            "description": "Text that comes AFTER the `text` field in TTSRequest. Provides forward context for emotion inference.\r\n\r\nThe model analyzes the flow: `previous_text` → `text` (synthesized) → `next_text`\r\n\r\n- Maximum 2000 characters\r\n- Helps the model anticipate emotional transitions\r\n- Leave empty if no following context is available\r\n"
          },
          "emotion_type": {
            "type": "string",
            "const": "smart",
            "title": "Emotion Type",
            "default": "smart",
            "description": "Discriminator field to identify the prompt type. Must be set to \"smart\" for context-aware emotion inference.\r\n"
          },
          "previous_text": {
            "type": "string",
            "title": "Previous Text",
            "default": "",
            "example": "I feel like I'm walking on air and I just want to scream with joy!",
            "description": "Text that comes BEFORE the `text` field in TTSRequest. Provides backward context for emotion inference.\r\n\r\nThe model analyzes the flow: `previous_text` → `text` (synthesized) → `next_text`\r\n\r\n- Maximum 2000 characters\r\n- Helps the model understand emotional build-up and context\r\n- Leave empty if no preceding context is available\r\n"
          }
        },
        "description": "Emotion and style settings for the generated speech.",
        "additionalProperties": false
      },
      "PresetPrompt": {
        "type": "object",
        "title": "PresetPrompt (ssfm-v30)",
        "properties": {
          "emotion_type": {
            "type": "string",
            "const": "preset",
            "title": "Emotion Type",
            "default": "preset",
            "description": "Discriminator field to identify the prompt type. Must be set to \"preset\" for preset-based emotion control.\r\n"
          },
          "emotion_preset": {
            "$ref": "#/components/schemas/EmotionEnum",
            "default": "normal",
            "example": "normal",
            "description": "Emotion preset to apply to the generated speech.\r\n\r\nSupported emotions: normal, happy, sad, angry, whisper, toneup, tonedown\r\n\r\nCheck available emotions for each voice in the `models` field of the `GET /v3/voices` API response.\r\n"
          },
          "emotion_intensity": {
            "type": "number",
            "title": "Emotion Intensity",
            "default": 1,
            "example": 1,
            "maximum": 2,
            "minimum": 0,
            "description": "Controls the strength of emotional expression in the generated speech.\r\n\r\n- 0.0: Completely neutral, no emotional coloring\r\n- 0.5: Subtle emotional hints\r\n- 1.0: Standard emotional expression (default)\r\n- 1.5: Strong emotional emphasis\r\n- 2.0: Maximum intensity, highly expressive\r\n"
          }
        },
        "description": "Emotion and style settings for the generated speech.",
        "additionalProperties": false
      },
      "UseCasesEnum": {
        "enum": [
          "Announcer",
          "Anime",
          "Audiobook",
          "Conversational",
          "Documentary",
          "E-learning",
          "Rapper",
          "Game",
          "Tiktok/Reels",
          "News",
          "Podcast",
          "Voicemail",
          "Ads"
        ],
        "type": "string",
        "description": "Voice use case categories for content type filtering. Each voice is tagged with one or more use cases indicating its suitability for specific content types.\n\n**Available Use Cases:**\n- **Announcer**: Public announcements and presentations\n- **Anime**: Animation and character voices\n- **Audiobook**: Long-form narration and storytelling\n- **Conversational**: Chatbots and conversational AI\n- **Documentary**: Documentary narration and commentary\n- **E-learning**: Educational content and tutorials\n- **Rapper**: Rap and music performance\n- **Game**: Video game characters and narration\n- **Tiktok/Reels**: Short-form social media content\n- **News**: News broadcasting\n- **Podcast**: Broadcasting and podcast production\n- **Voicemail**: IVR systems and voice assistants\n- **Ads**: Advertising and promotional content\n"
      },
      "ErrorResponse": {
        "type": "object",
        "example": {
          "message": "The input text contains characters or symbols that cannot be synthesized into speech. Please check your input text.",
          "error_code": "TEXT_NOT_SYNTHESIZABLE"
        },
        "properties": {
          "detail": {
            "type": "string",
            "description": "Error message describing the issue"
          },
          "message": {
            "type": "string",
            "description": "Human-readable message for structured errors"
          },
          "error_code": {
            "type": "string",
            "description": "Machine-readable error code for structured errors"
          }
        },
        "description": "API errors use `detail` for legacy and validation errors, or `error_code` and `message` for structured errors."
      },
      "CustomVoiceItem": {
        "type": "object",
        "title": "CustomVoiceItem",
        "required": [
          "voice_id",
          "name",
          "model",
          "source",
          "status",
          "created_at"
        ],
        "properties": {
          "name": {
            "type": "string",
            "title": "Name",
            "description": "Voice name."
          },
          "error": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Error",
            "description": "Failure reason when `status` is `failed`."
          },
          "model": {
            "type": "string",
            "title": "Model",
            "description": "TTS model version."
          },
          "source": {
            "type": "string",
            "title": "Source",
            "description": "Creation method (`instant` or `professional`)."
          },
          "status": {
            "$ref": "#/components/schemas/CustomVoiceStatus",
            "description": "Current creation or training status."
          },
          "voice_id": {
            "type": "string",
            "title": "Voice Id",
            "description": "Unique custom voice identifier with the `uc_` prefix."
          },
          "created_at": {
            "type": "string",
            "title": "Created At",
            "format": "date-time",
            "description": "Creation time in UTC."
          }
        },
        "description": "A custom voice owned by the authenticated account."
      },
      "ValidationError": {
        "type": "object",
        "title": "ValidationError",
        "required": [
          "loc",
          "msg",
          "type"
        ],
        "properties": {
          "ctx": {
            "type": "object",
            "title": "Context"
          },
          "loc": {
            "type": "array",
            "items": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "integer"
                }
              ]
            },
            "title": "Location"
          },
          "msg": {
            "type": "string",
            "title": "Message"
          },
          "type": {
            "type": "string",
            "title": "Error Type"
          },
          "input": {
            "title": "Input"
          }
        }
      },
      "RecommendedVoice": {
        "type": "object",
        "title": "RecommendedVoice",
        "required": [
          "voice_id",
          "voice_name",
          "score"
        ],
        "properties": {
          "score": {
            "type": "number",
            "title": "Score",
            "example": 0.92,
            "description": "Recommendation relevance score. Higher values indicate a stronger match for the query."
          },
          "voice_id": {
            "type": "string",
            "title": "Voice Id",
            "example": "tc_60e5426de8b95f1d3000d7b5",
            "description": "Typecast voice identifier with the `tc_` prefix. Use this value as `voice_id` in text-to-speech requests."
          },
          "voice_name": {
            "type": "string",
            "title": "Voice Name",
            "example": "Olivia",
            "description": "Human-readable voice name."
          }
        },
        "description": "Recommended voice candidate returned by `GET /v1/voices/recommendations`, sorted by relevance."
      },
      "CustomVoiceStatus": {
        "enum": [
          "pending",
          "training",
          "completed",
          "failed"
        ],
        "type": "string",
        "title": "CustomVoiceStatus",
        "description": "Current creation or training status of a custom voice."
      },
      "CustomVoiceResponse": {
        "type": "object",
        "title": "CustomVoiceResponse",
        "required": [
          "voice_id",
          "name",
          "model",
          "status"
        ],
        "properties": {
          "name": {
            "type": "string",
            "title": "Name",
            "description": "Human-readable voice name (1-30 characters)."
          },
          "model": {
            "type": "string",
            "allOf": [
              {
                "$ref": "#/components/schemas/TTSModel"
              }
            ],
            "title": "Model",
            "description": "Engine model the voice was cloned for (`ssfm-v21` or `ssfm-v30`)."
          },
          "status": {
            "$ref": "#/components/schemas/CustomVoiceStatus",
            "description": "생성/학습 상태"
          },
          "voice_id": {
            "type": "string",
            "title": "Voice Id",
            "example": "uc_64a1b2c3d4e5f6a7b8c9d0e1",
            "description": "Custom voice identifier with the `uc_` prefix. Use this value as `voice_id` in `POST /v1/text-to-speech` and other endpoints that accept `voice_id`."
          }
        },
        "description": "Response of `POST /v1/voices/clone` — custom voice metadata returned by instant cloning."
      },
      "HTTPValidationError": {
        "type": "object",
        "title": "HTTPValidationError",
        "properties": {
          "detail": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ValidationError"
            },
            "title": "Detail"
          }
        }
      },
      "PauseComposeSegment": {
        "type": "object",
        "title": "PauseComposeSegment",
        "examples": [
          {
            "type": "pause",
            "duration_seconds": 1.5
          }
        ],
        "required": [
          "type",
          "duration_seconds"
        ],
        "properties": {
          "type": {
            "type": "string",
            "const": "pause",
            "title": "Type",
            "default": "pause",
            "description": "Segment discriminator. Always `pause`."
          },
          "duration_seconds": {
            "type": "number",
            "title": "Duration Seconds",
            "example": 1.5,
            "maximum": 10,
            "description": "Pause duration in seconds. Each pause may be up to 10 seconds; all pauses combined may be up to 60 seconds.",
            "exclusiveMinimum": 0
          }
        },
        "description": "A silent interval inserted without consuming credits.",
        "additionalProperties": false
      },
      "AlignmentSegmentWord": {
        "type": "object",
        "title": "AlignmentSegmentWord",
        "required": [
          "text",
          "start",
          "end"
        ],
        "properties": {
          "end": {
            "type": "number",
            "title": "End",
            "description": "End time of this segment, in seconds from the beginning of the audio."
          },
          "text": {
            "type": "string",
            "title": "Text",
            "description": "The text fragment from the original transcript (includes any attached punctuation)."
          },
          "start": {
            "type": "number",
            "title": "Start",
            "description": "Start time of this segment, in seconds from the beginning of the audio."
          }
        },
        "description": "A single word-level alignment segment between the original transcript and the generated audio."
      },
      "SubscriptionResponse": {
        "type": "object",
        "title": "SubscriptionResponse",
        "required": [
          "plan",
          "credits",
          "limits",
          "professional_clone_generations"
        ],
        "properties": {
          "plan": {
            "$ref": "#/components/schemas/PlanTier",
            "description": "Current subscription plan"
          },
          "limits": {
            "$ref": "#/components/schemas/Limits",
            "description": "Usage limit information"
          },
          "credits": {
            "$ref": "#/components/schemas/Credits",
            "description": "Credit usage information"
          },
          "professional_clone_generations": {
            "$ref": "#/components/schemas/ProfessionalCloneGenerations"
          }
        },
        "description": "Subscription information response model"
      },
      "AlignmentSegmentCharacter": {
        "type": "object",
        "title": "AlignmentSegmentCharacter",
        "required": [
          "text",
          "start",
          "end"
        ],
        "properties": {
          "end": {
            "type": "number",
            "title": "End",
            "description": "End time of this segment, in seconds from the beginning of the audio."
          },
          "text": {
            "type": "string",
            "title": "Text",
            "description": "The text fragment from the original transcript (includes any attached punctuation and whitespace)."
          },
          "start": {
            "type": "number",
            "title": "Start",
            "description": "Start time of this segment, in seconds from the beginning of the audio."
          }
        },
        "description": "A single character-level alignment segment between the original transcript and the generated audio."
      },
      "CustomVoiceCreateResponse": {
        "type": "object",
        "title": "CustomVoiceCreateResponse",
        "required": [
          "voice_id",
          "name",
          "model",
          "status"
        ],
        "properties": {
          "name": {
            "type": "string",
            "title": "Name",
            "description": "Voice name."
          },
          "model": {
            "type": "string",
            "title": "Model",
            "description": "TTS model version."
          },
          "status": {
            "$ref": "#/components/schemas/CustomVoiceStatus",
            "description": "Current creation or training status."
          },
          "voice_id": {
            "type": "string",
            "title": "Voice Id",
            "description": "Unique custom voice identifier with the `uc_` prefix."
          }
        },
        "description": "Result returned after creating an instant or professional custom voice."
      },
      "TTSWithTimestampsResponse": {
        "type": "object",
        "title": "TTSWithTimestampsResponse",
        "required": [
          "audio",
          "audio_format",
          "audio_duration",
          "words",
          "characters"
        ],
        "properties": {
          "audio": {
            "type": "string",
            "title": "Audio",
            "description": "Base64-encoded audio bytes. Decode and write to a file using the `audio_format` extension."
          },
          "words": {
            "anyOf": [
              {
                "type": "array",
                "items": {
                  "$ref": "#/components/schemas/AlignmentSegmentWord"
                }
              },
              {
                "type": "null"
              }
            ],
            "title": "Words",
            "description": "Word-level timestamps (with attached punctuation). `null` when the request uses `granularity=char`."
          },
          "characters": {
            "anyOf": [
              {
                "type": "array",
                "items": {
                  "$ref": "#/components/schemas/AlignmentSegmentCharacter"
                }
              },
              {
                "type": "null"
              }
            ],
            "title": "Characters",
            "description": "Character-level timestamps (including punctuation and whitespace). `null` when the request uses `granularity=word`."
          },
          "audio_format": {
            "enum": [
              "wav",
              "mp3"
            ],
            "type": "string",
            "title": "Audio Format",
            "description": "Audio encoding format of the bytes in `audio` — either `wav` or `mp3`, mirroring the request's `output.audio_format`."
          },
          "audio_duration": {
            "type": "number",
            "title": "Audio Duration",
            "description": "Length of the generated audio in seconds."
          }
        },
        "description": "Response payload for POST /v1/text-to-speech/with-timestamps — base64-encoded audio plus per-word and per-character timestamps aligned with the generated speech."
      },
      "ProfessionalCloneGenerations": {
        "type": "object",
        "title": "ProfessionalCloneGenerations",
        "properties": {
          "plan_generations": {
            "type": "integer",
            "title": "Plan Generations",
            "default": 0,
            "minimum": 0,
            "description": "플랜 제공 학습 횟수"
          },
          "used_generations": {
            "type": "integer",
            "title": "Used Generations",
            "default": 0,
            "minimum": 0,
            "description": "사용된 학습 횟수"
          }
        },
        "description": "프리미엄 클로닝 학습 횟수 정보"
      },
      "Body_create_voice_clone_v1_voices_clone_post": {
        "type": "object",
        "title": "Body_create_voice_clone_v1_voices_clone_post",
        "required": [
          "file",
          "name",
          "model"
        ],
        "properties": {
          "file": {
            "type": "string",
            "title": "File",
            "format": "binary",
            "description": "Audio sample. WAV or MP3, max 25 MB, 5-150 seconds.",
            "contentMediaType": "application/octet-stream"
          },
          "name": {
            "type": "string",
            "title": "Name",
            "maxLength": 30,
            "minLength": 1,
            "description": "Voice name (1-30 characters)."
          },
          "model": {
            "$ref": "#/components/schemas/TTSModel",
            "allOf": [
              {
                "$ref": "#/components/schemas/TTSModel"
              }
            ],
            "description": "Engine model the voice is cloned for (`ssfm-v21` or `ssfm-v30`)."
          }
        },
        "description": "Multipart request body for instant cloning."
      },
      "Body_create_instant_clone_v1_custom_voices_instant_clone_post": {
        "type": "object",
        "title": "Body_create_instant_clone_v1_custom_voices_instant_clone_post",
        "required": [
          "file",
          "name",
          "model"
        ],
        "properties": {
          "file": {
            "type": "string",
            "title": "File",
            "format": "binary",
            "description": "One WAV or MP3 recording, 25 MiB or less and 5 to 150 seconds long.",
            "contentMediaType": "application/octet-stream"
          },
          "name": {
            "type": "string",
            "title": "Name",
            "example": "Product Narrator",
            "maxLength": 30,
            "minLength": 1,
            "description": "Voice name, up to 30 characters."
          },
          "model": {
            "$ref": "#/components/schemas/TTSModel",
            "example": "ssfm-v30",
            "description": "TTS model version."
          }
        },
        "description": "Multipart request body for instant voice cloning."
      },
      "Body_create_professional_clone_v1_custom_voices_professional_clone_post": {
        "type": "object",
        "title": "Body_create_professional_clone_v1_custom_voices_professional_clone_post",
        "required": [
          "name",
          "files",
          "model",
          "language"
        ],
        "properties": {
          "name": {
            "type": "string",
            "title": "Name",
            "example": "Custom Voice Name",
            "maxLength": 30,
            "minLength": 1,
            "description": "Voice name, up to 30 characters."
          },
          "files": {
            "type": "array",
            "items": {
              "type": "string",
              "format": "binary",
              "contentMediaType": "application/octet-stream"
            },
            "title": "Files",
            "description": "WAV or MP3 recordings used for training. Only one file can be uploaded.\r\n\r\n**Upload limits**\r\n\r\n* One WAV or MP3 file\r\n* File size: 1 GiB or less\r\n* Duration: 5 minutes to 3 hours\r\n* Sample rate: 16 kHz or higher\r\n\r\nFor best results, we recommend audio that meets the following conditions:\r\n\r\n* Record in a speaking style that closely matches how you want the generated voice to sound.\r\n* Record in a quiet environment without background noise.\r\n* Include only one speaker.\r\n* Record in the language specified in the `language` field.\r\n* Longer input audio results in higher-quality generated voices."
          },
          "model": {
            "$ref": "#/components/schemas/TTSModel",
            "example": "ssfm-v30",
            "description": "TTS model version."
          },
          "language": {
            "type": "string",
            "title": "Language",
            "example": "eng",
            "description": "ISO 639-3 language code, such as `kor` or `eng`."
          }
        },
        "description": "Multipart request body for professional voice cloning."
      }
    },
    "securitySchemes": {
      "ApiKeyAuth": {
        "in": "header",
        "name": "X-API-KEY",
        "type": "apiKey",
        "description": "API key for authentication. You can obtain an API key from the Typecast API Console."
      },
      "BearerAuth": {
        "type": "http",
        "scheme": "bearer",
        "bearerFormat": "JWT"
      }
    }
  }
}
```