{ "openapi": "3.0.1", "info": { "title": "X Video Subtitle & Caption Transcript Converter", "description": "Convert public X (Twitter) videos into timestamped transcripts and downloadable SRT/VTT subtitle files, using native captions when available and AI speech-to-text otherwise.", "version": "1.0", "x-build-id": "IeVVIA2c2aj2ljt2y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nimbryxo-studio~x-video-subtitle-and-caption-transcript-converter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nimbryxo-studio-x-video-subtitle-and-caption-transcript-converter", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nimbryxo-studio~x-video-subtitle-and-caption-transcript-converter/runs": { "post": { "operationId": "runs-sync-nimbryxo-studio-x-video-subtitle-and-caption-transcript-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nimbryxo-studio~x-video-subtitle-and-caption-transcript-converter/run-sync": { "post": { "operationId": "run-sync-nimbryxo-studio-x-video-subtitle-and-caption-transcript-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "postUrls" ], "properties": { "postUrls": { "title": "Post links", "minItems": 1, "type": "array", "description": "One or more Twitter/X post links that contain a video or GIF. Both x.com and twitter.com links are accepted. Profile links or usernames also work: the actor transcribes the profile's latest video post.", "items": { "type": "string" } }, "profileUrls": { "title": "Profile links or usernames", "type": "array", "description": "Optional. Transcribe the latest video post from these profiles. Paste x.com profile links or bare usernames.", "items": { "type": "string" } }, "transcriptionMethod": { "title": "How to transcribe", "enum": [ "auto", "captions", "ai" ], "type": "string", "description": "Auto tries the video's built-in captions first and only falls back to Whisper AI when none exist. Captions-only skips videos without captions. AI-only always uses Whisper speech-to-text.", "default": "auto" }, "whisperModel": { "title": "AI model size", "enum": [ "tiny", "base", "small", "medium", "large-v2" ], "type": "string", "description": "Whisper model used for AI transcription. Larger models are more accurate but slower and need more memory (medium and large-v2 need a run memory of at least 4096 MB and 8192 MB respectively). Base is a good balance for most videos. If the selected model does not fit the run memory, the actor automatically falls back to the next smaller model. Long videos are split into 10-minute chunks automatically, so there is no length limit.", "default": "base" }, "language": { "title": "Spoken language hint (AI only)", "type": "string", "description": "Optional language code for AI transcription, for example en, es, fr or ur. Improves accuracy when the spoken language is known. Leave empty to detect it automatically. Ignored when native captions are used." }, "outputFormat": { "title": "Output format", "enum": [ "segments", "fullText", "both", "srt", "vtt" ], "type": "string", "description": "Segments gives timestamped lines, full text gives one transcript string, and both gives you both in the same row.", "default": "segments" }, "includeTweetMetadata": { "title": "Include post details", "type": "boolean", "description": "Attach the post's author, text and publish date to every transcript row.", "default": true }, "segmentGranularity": { "title": "Segment granularity", "enum": [ "segment", "sentence", "word" ], "type": "string", "description": "Level of the timestamped segments. Segment keeps the raw caption/Whisper cues. Sentence groups real word timings into sentences (or splits cue text, sharing the cue's real time range). Word emits one entry per real word timestamp and is used only when X captions or Whisper provide per-word timings — it is never fabricated; when word timings are missing, the row says so and keeps the raw segments.", "default": "segment" }, "includeWordTimestamps": { "title": "Include word timestamps", "type": "boolean", "description": "Add per-word start/end times to AI (Whisper) transcript segments. Automatically enabled when Segment granularity is Sentence or Word. Native captions only carry words when X included inline timing markers.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Use an Apify proxy if you plan large runs or see frequent rate limits." } } }, "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 } } } } } } } } } }