{
  "openapi": "3.0.1",
  "info": {
    "title": "Media Transcriber - Audio, Video & Podcast to Text, SRT, VTT",
    "description": "Transcribe audio, video and podcast feeds to text with timestamps, SRT and VTT. Bring your Groq/OpenAI key for full-length Whisper, or use the built-in small model. Language detection, English translation. From US$2 per 1,000 audio minutes.",
    "version": "0.1",
    "x-build-id": "rkM3YobCA4djX5CRZ"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/fabrikit~media-transcriber/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-fabrikit-media-transcriber",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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/fabrikit~media-transcriber/runs": {
      "post": {
        "operationId": "runs-sync-fabrikit-media-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/fabrikit~media-transcriber/run-sync": {
      "post": {
        "operationId": "run-sync-fabrikit-media-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": {
          "urls": {
            "title": "Audio / video / podcast URLs",
            "type": "array",
            "description": "Direct links to mp3, mp4, m4a, wav, webm, ogg, flac, mov... files, Google Drive or Dropbox share links (public), or a podcast RSS feed URL (the latest episodes are transcribed). YouTube links are not supported.",
            "items": {
              "type": "object",
              "required": [
                "url"
              ],
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL of a web page",
                  "format": "uri"
                }
              }
            }
          },
          "files": {
            "title": "Uploaded files",
            "type": "array",
            "description": "Optional: upload audio/video files from your computer (stored in a key-value store of your account). Each uploaded file must be publicly reachable by URL, which is what the upload dialog provides."
          },
          "apiKey": {
            "title": "Your Groq or OpenAI API key (optional)",
            "type": "string",
            "description": "Bring your own key to transcribe full-length media with Whisper large-v3-turbo (Groq, free tier available) or whisper-1 (OpenAI). Keys starting with gsk_ are used with Groq, sk- with OpenAI. The key is stored encrypted, kept in memory only and never logged or saved. Leave empty to use the built-in local model."
          },
          "provider": {
            "title": "Engine",
            "enum": [
              "auto",
              "groq",
              "openai",
              "local"
            ],
            "type": "string",
            "description": "Auto uses Groq/OpenAI when you provide a key (detected from its prefix) and the built-in local model otherwise.",
            "default": "auto"
          },
          "language": {
            "title": "Spoken language",
            "type": "string",
            "description": "\"auto\" detects the language. Or give a Whisper language code such as en, es, de, fr, pt, it, ja, zh. Setting it improves accuracy for short or noisy audio.",
            "default": "auto"
          },
          "translateToEnglish": {
            "title": "Translate to English",
            "type": "boolean",
            "description": "Return the English translation instead of the original-language transcript (Whisper translation). The detected source language is then not reported.",
            "default": false
          },
          "prompt": {
            "title": "Vocabulary hint (API engines)",
            "type": "string",
            "description": "Optional names, jargon or style hint (up to ~200 words) that helps the API model spell rare words correctly. Ignored by the local model."
          },
          "wordTimestamps": {
            "title": "Word-level timestamps (API engines)",
            "type": "boolean",
            "description": "Also return a `words` array with start/end for every word. Only with a Groq/OpenAI key.",
            "default": false
          },
          "maxItems": {
            "title": "Max files to transcribe",
            "minimum": 1,
            "maximum": 1000,
            "type": "integer",
            "description": "Upper limit of audio/video files processed in this run (podcast episodes count one each).",
            "default": 3
          },
          "maxEpisodesPerFeed": {
            "title": "Episodes per podcast feed",
            "minimum": 1,
            "maximum": 500,
            "type": "integer",
            "description": "How many of the newest episodes to transcribe when a URL is an RSS feed.",
            "default": 3
          },
          "maxMinutesPerItem": {
            "title": "Max minutes per file (0 = no limit)",
            "minimum": 0,
            "maximum": 720,
            "type": "integer",
            "description": "Transcribe only the first N minutes of each file to cap your spend. 0 means the full file (local mode is always capped at 10 minutes).",
            "default": 0
          },
          "chunkMinutes": {
            "title": "Chunk length for long files (minutes)",
            "minimum": 5,
            "maximum": 60,
            "type": "integer",
            "description": "Long media is cut at silences into chunks of about this length before it is sent to the API (API upload limit is 25 MB per request).",
            "default": 20
          },
          "localModel": {
            "title": "Local model size",
            "enum": [
              "base",
              "tiny"
            ],
            "type": "string",
            "description": "Only for the no-key mode. Base is more accurate; tiny is a bit faster.",
            "default": "base"
          },
          "includeSegments": {
            "title": "Include timestamped segments",
            "type": "boolean",
            "description": "Add the `segments` array (start, end, text) to every dataset item.",
            "default": true
          },
          "includeSubtitles": {
            "title": "Include SRT and VTT text in the dataset",
            "type": "boolean",
            "description": "Add `srt` and `vtt` strings to every dataset item.",
            "default": true
          },
          "saveFilesToKeyValueStore": {
            "title": "Save .txt / .srt / .vtt files",
            "type": "boolean",
            "description": "Also store the transcript as downloadable .txt, .srt and .vtt files in the run's key-value store (links are returned as txtUrl, srtUrl, vttUrl).",
            "default": true
          },
          "maxFileSizeMb": {
            "title": "Max download size (MB)",
            "minimum": 1,
            "maximum": 5000,
            "type": "integer",
            "description": "Files larger than this are skipped.",
            "default": 1000
          },
          "proxyConfiguration": {
            "title": "Proxy configuration",
            "type": "object",
            "description": "Only used to download your URLs. The actor downloads directly first and escalates to Apify datacenter and then residential proxies only if the host blocks it.",
            "default": {
              "useApifyProxy": true
            }
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}