{
"openapi": "3.0.1",
"info": {
"title": "Subtitle Generator - SRT/VTT (Whisper, bilingual, CJK-aware)",
"description": "Turn audio or video files into clean SRT/VTT subtitles with Whisper on CPU. Readable cue splitting (line length, CJK-aware), word timestamps, English translation and bilingual subtitles. No API key needed.",
"version": "0.1",
"x-build-id": "EB3eqeXjVTp526cg8"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/mocking_bird~whisper-subtitles/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-mocking_bird-whisper-subtitles",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/mocking_bird~whisper-subtitles/runs": {
"post": {
"operationId": "runs-sync-mocking_bird-whisper-subtitles",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/mocking_bird~whisper-subtitles/run-sync": {
"post": {
"operationId": "run-sync-mocking_bird-whisper-subtitles",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"required": [
"mediaUrls"
],
"properties": {
"mediaUrls": {
"title": "Media URLs",
"type": "array",
"description": "Direct links to audio or video files (mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv...). One subtitle set per file. Video pages such as YouTube links are not supported - use a direct file link.",
"items": {
"type": "string"
}
},
"language": {
"title": "Spoken language",
"type": "string",
"description": "ISO 639-1 code such as en, ja, es. Leave empty to auto-detect.",
"default": ""
},
"quality": {
"title": "Quality / speed",
"enum": [
"fast",
"balanced",
"accurate"
],
"type": "string",
"description": "Balanced (Whisper small, beam search) suits clean English and most podcasts. Fast is the same model with greedy decoding: quickest and cheapest. Accurate (Whisper large-v3-turbo) is about 3x slower and costs more per minute, but is far better for Japanese, Chinese, accents, names and noisy audio.",
"default": "balanced"
},
"translateToEnglish": {
"title": "Also translate to English",
"type": "boolean",
"description": "Adds an English transcript and English SRT/VTT (second pass, charged per minute).",
"default": false
},
"bilingualSubtitles": {
"title": "Bilingual subtitles (original + English)",
"type": "boolean",
"description": "Produces an extra SRT where every cue shows the original line followed by its English translation. Great for language learning and travel videos. Implies translation.",
"default": false
},
"maxCharsPerLine": {
"title": "Max characters per line",
"minimum": 10,
"maximum": 120,
"type": "integer",
"description": "Line width of a subtitle. 42 is the broadcast standard for Latin scripts; wide (CJK) characters count double, so 42 means about 21 Japanese characters. Use 32 for vertical / mobile video.",
"default": 42
},
"maxLinesPerCue": {
"title": "Max lines per cue",
"minimum": 1,
"maximum": 4,
"type": "integer",
"description": "How many lines one subtitle may have. 2 is standard.",
"default": 2
},
"maxCueDurationSec": {
"title": "Max cue duration (seconds)",
"minimum": 2,
"maximum": 20,
"type": "integer",
"description": "Cues longer than this are split, even mid-sentence.",
"default": 6
},
"wordTimestamps": {
"title": "Include word-level timestamps",
"type": "boolean",
"description": "Adds a words array (start, end, text) to each record - for karaoke-style captions or word highlighting.",
"default": false
},
"vocabularyHint": {
"title": "Vocabulary hint",
"type": "string",
"description": "Names, brands or jargon that appear in the audio, comma separated. Helps spelling."
},
"vadFilter": {
"title": "Skip silence (VAD)",
"type": "boolean",
"description": "Removes long silences before transcription. Faster and avoids hallucinated text in quiet parts.",
"default": true
},
"saveFilesToKeyValueStore": {
"title": "Save .srt / .vtt / .txt files",
"type": "boolean",
"description": "Stores downloadable files in the run's key-value store and adds their URLs to each record.",
"default": true
},
"maxDurationMinutes": {
"title": "Max media duration (minutes)",
"minimum": 1,
"maximum": 600,
"type": "integer",
"description": "Files longer than this are rejected before transcription (not charged).",
"default": 180
},
"maxFileSizeMb": {
"title": "Max file size (MB)",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Downloads are aborted above this size (not charged).",
"default": 500
},
"downloadTimeoutSec": {
"title": "Download timeout (seconds)",
"minimum": 10,
"maximum": 900,
"type": "integer",
"description": "Raise it for very large files on slow hosts.",
"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
}
}
}
}
}
}
}
}
}
}