{
  "openapi": "3.0.1",
  "info": {
    "title": "Video to Captions (SRT, VTT, TXT) - Whisper AI",
    "description": "Video to SRT, VTT, TXT and word-level JSON from any video or audio URL. Whisper transcription with auto language detection, English translation, trim to save cost and subtitle-ready line breaks. Batch. MCP, n8n, Make, API. No install. Failed files free.",
    "version": "0.1",
    "x-build-id": "vnv7bhzYkifeoYdnb"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/ent-e~video-to-captions-whisper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-ent-e-video-to-captions-whisper",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/ent-e~video-to-captions-whisper/runs": {
      "post": {
        "operationId": "runs-sync-ent-e-video-to-captions-whisper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/ent-e~video-to-captions-whisper/run-sync": {
      "post": {
        "operationId": "run-sync-ent-e-video-to-captions-whisper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
          "url": {
            "title": "Audio or video URL",
            "type": "string",
            "description": "Direct, publicly downloadable URL of ONE audio or video file (http/https; redirects followed). Any FFmpeg-readable format: mp4, mov, mkv, webm, mp3, wav, m4a, ogg, flac, opus... Max 2 GB. Must be the media file itself, not a YouTube/TikTok/web page. Example: https://archive.org/download/short_stories14_librivox/maxims_wilde_tb_64kb.mp3"
          },
          "files": {
            "title": "Batch of files",
            "type": "array",
            "description": "Optional batch, processed sequentially. Array of objects {\"url\": string (required), plus any of model, language, task, startSeconds, durationSeconds, maxCharsPerLine, maxLinesPerCue, maxCueSeconds, wordsPerCue, vadFilter, beamSize, initialPrompt, txtTimestamps to override the top-level value for that file}. Plain URL strings are also accepted. Example: [{\"url\":\"https://example.com/talk.mp4\"},{\"url\":\"https://example.com/entrevista.mp3\",\"language\":\"es\",\"task\":\"translate\"}]. Failed items return status=error and are not charged."
          },
          "model": {
            "title": "Whisper model",
            "enum": [
              "tiny",
              "base",
              "small",
              "large-v3-turbo",
              "tiny.en",
              "base.en",
              "small.en"
            ],
            "type": "string",
            "description": "Open-source Whisper model run with faster-whisper (CTranslate2, int8, CPU). Default: small - good accuracy for clear speech in most languages. Use base/tiny for speed or rough drafts. Use large-v3-turbo for accented, noisy, technical or non-English speech; it is billed at the higher 'audio-minute-hq' rate, runs about 2-3x slower than small and is downloaded at run start (adds ~30-60 s). *.en models are English-only. tiny, base and small are preloaded.",
            "default": "small"
          },
          "language": {
            "title": "Language",
            "type": "string",
            "description": "Spoken language as an ISO 639-1 code (e.g. en, es, de, fr, pt, ja, zh, hi), or 'auto' (default) to auto-detect from the first 30 seconds. Setting it explicitly is faster and avoids misdetection on short or music-heavy clips. The detected language is returned in the output.",
            "default": "auto"
          },
          "task": {
            "title": "Task",
            "enum": [
              "transcribe",
              "translate"
            ],
            "type": "string",
            "description": "transcribe = captions in the spoken language (default). translate = English captions for non-English speech (Whisper's built-in speech translation; works with tiny, base, small, medium and large-v3; English-only models and large-v3-turbo are not trained for it).",
            "default": "transcribe"
          },
          "startSeconds": {
            "title": "Start at (s)",
            "minimum": 0,
            "type": "number",
            "description": "Optional: start transcribing at this many seconds into the file (e.g. 120). Caption timestamps stay relative to the ORIGINAL file, so they line up with the untrimmed video. Default: 0."
          },
          "durationSeconds": {
            "title": "Duration (s)",
            "minimum": 1,
            "type": "number",
            "description": "Optional: only transcribe this many seconds from startSeconds (e.g. 60). Billing is per started minute of transcribed audio, so trimming lowers cost. Default: to the end of the file."
          },
          "maxCharsPerLine": {
            "title": "Max characters per line",
            "minimum": 10,
            "maximum": 120,
            "type": "integer",
            "description": "Caption line length for SRT/VTT. Default 42 (Netflix/BBC guideline). Use 32 for mobile/vertical video, 20-25 for big short-form captions.",
            "default": 42
          },
          "maxLinesPerCue": {
            "title": "Max lines per caption",
            "minimum": 1,
            "maximum": 4,
            "type": "integer",
            "description": "Maximum lines shown at once in each SRT/VTT caption. Default 2 (broadcast standard); 1 for short-form/social video.",
            "default": 2
          },
          "maxCueSeconds": {
            "title": "Max caption duration (s)",
            "minimum": 1,
            "maximum": 30,
            "type": "number",
            "description": "Maximum time a single caption stays on screen, in seconds. Default 6. Captions are split on word timestamps and sentence ends.",
            "default": 6
          },
          "wordsPerCue": {
            "title": "Words per caption (short-form style)",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "Optional: fixed maximum number of words per caption (e.g. 1-4 for TikTok/Reels/Shorts style pop-on captions). Leave empty for standard subtitles filled up to maxCharsPerLine x maxLinesPerCue."
          },
          "vadFilter": {
            "title": "Skip silence (VAD)",
            "type": "boolean",
            "description": "Use Silero voice-activity detection to skip non-speech parts. Default true: faster and prevents Whisper from hallucinating text during silence/music. Disable only if quiet speech is being dropped.",
            "default": true
          },
          "beamSize": {
            "title": "Beam size",
            "minimum": 1,
            "maximum": 10,
            "type": "integer",
            "description": "Decoding beam width. Default 5 (most accurate). 1 = greedy decoding, roughly 1.5-2x faster with slightly lower accuracy.",
            "default": 5
          },
          "initialPrompt": {
            "title": "Vocabulary hint (initial prompt)",
            "type": "string",
            "description": "Optional text that primes Whisper with spelling of names, brands and jargon, e.g. 'Guests: Siobhan O'Neill, Kubernetes, PyTorch, ENT-E.' Keep it short (under ~200 words). Also nudges punctuation/casing style."
          },
          "txtTimestamps": {
            "title": "Timestamps in TXT",
            "type": "boolean",
            "description": "If true, the .txt transcript has one segment per line prefixed with [HH:MM:SS]. Default false: clean paragraphs (new paragraph after pauses > 2 s), ideal for LLM summarization.",
            "default": false
          },
          "maxDurationSeconds": {
            "title": "Max audio duration (s)",
            "minimum": 1,
            "type": "integer",
            "description": "Safety cap on the duration to transcribe, in seconds (default 10800 = 3 hours). Longer inputs are rejected with status=error and not charged unless trimmed with durationSeconds. Set the run timeout accordingly for long files (see README for speed per model).",
            "default": 10800
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}