{
  "openapi": "3.0.1",
  "info": {
    "title": "Audio & Podcast Transcriber (Speech to Text)",
    "description": "Transcribe audio and video links or podcast RSS feeds to text with Whisper. Timed segments, SRT and VTT subtitles, auto language detection. No login, no API key.",
    "version": "0.0",
    "x-build-id": "JU1sxj4bFDBXXs2wU"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/cliqtomedia~audio-video-transcriber/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-cliqtomedia-audio-video-transcriber",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/cliqtomedia~audio-video-transcriber/runs": {
      "post": {
        "operationId": "runs-sync-cliqtomedia-audio-video-transcriber",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/cliqtomedia~audio-video-transcriber/run-sync": {
      "post": {
        "operationId": "run-sync-cliqtomedia-audio-video-transcriber",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "audioUrls": {
            "title": "Audio or video file URLs",
            "maxItems": 100,
            "type": "array",
            "description": "Up to 100 public http(s) links straight to a media file: MP3, M4A, WAV, OGG, Opus, MP4 and other common audio and video formats. Page links from YouTube, TikTok, Spotify, Instagram and similar sites are not supported. No login, cookies or private networks; duplicates are processed once.",
            "items": {
              "type": "string"
            }
          },
          "podcastRssUrl": {
            "title": "Podcast RSS feed URL",
            "type": "string",
            "description": "Optional. A podcast RSS feed URL, or an Apple Podcasts show link (podcasts.apple.com/.../id123). The newest episodes are transcribed, up to Max episodes."
          },
          "maxEpisodes": {
            "title": "Max episodes",
            "minimum": 1,
            "maximum": 50,
            "type": "integer",
            "description": "How many of the newest feed episodes to transcribe. Used only with a podcast RSS feed.",
            "default": 3
          },
          "model": {
            "title": "Model",
            "enum": [
              "tiny",
              "base",
              "small"
            ],
            "type": "string",
            "description": "Whisper model size. tiny and base share one price per minute; small is charged at a higher price per minute.",
            "default": "base"
          },
          "language": {
            "title": "Language",
            "enum": [
              "auto",
              "af",
              "sq",
              "am",
              "ar",
              "hy",
              "as",
              "az",
              "ba",
              "eu",
              "be",
              "bn",
              "bs",
              "br",
              "bg",
              "my",
              "yue",
              "ca",
              "zh",
              "hr",
              "cs",
              "da",
              "nl",
              "en",
              "et",
              "fo",
              "fi",
              "fr",
              "gl",
              "ka",
              "de",
              "el",
              "gu",
              "ht",
              "ha",
              "haw",
              "he",
              "hi",
              "hu",
              "is",
              "id",
              "it",
              "ja",
              "jw",
              "kn",
              "kk",
              "km",
              "ko",
              "lo",
              "la",
              "lv",
              "ln",
              "lt",
              "lb",
              "mk",
              "mg",
              "ms",
              "ml",
              "mt",
              "mi",
              "mr",
              "mn",
              "ne",
              "no",
              "nn",
              "oc",
              "ps",
              "fa",
              "pl",
              "pt",
              "pa",
              "ro",
              "ru",
              "sa",
              "sr",
              "sn",
              "sd",
              "si",
              "sk",
              "sl",
              "so",
              "es",
              "su",
              "sw",
              "sv",
              "tl",
              "tg",
              "ta",
              "tt",
              "te",
              "th",
              "bo",
              "tr",
              "tk",
              "uk",
              "ur",
              "uz",
              "vi",
              "cy",
              "yi",
              "yo"
            ],
            "type": "string",
            "description": "Spoken language. Detect automatically uses the first 30 seconds; pick the language when you know it for better results.",
            "default": "auto"
          },
          "outputFormat": {
            "title": "Output format",
            "enum": [
              "segments",
              "text",
              "srt",
              "vtt"
            ],
            "type": "string",
            "description": "Every row has the full text. segments adds a list of {start, end, text}; srt or vtt adds a ready subtitle file in the subtitles field.",
            "default": "segments"
          },
          "translateToEnglish": {
            "title": "Translate to English",
            "type": "boolean",
            "description": "Return an English translation instead of a transcript in the original language (Whisper translate task).",
            "default": false
          },
          "maxDurationMinutes": {
            "title": "Max minutes per file",
            "minimum": 1,
            "maximum": 180,
            "type": "integer",
            "description": "Only the first N minutes of each file are transcribed and charged; longer files return status partial. Up to 180.",
            "default": 120
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}