TikTok & YouTube Transcript API - Video to Text, Captions & OCR
Pricing
from $10.00 / 1,000 video transcripts
Turn TikTok and YouTube videos and Shorts into text. Uses captions when present and speech recognition when not, so every video gets a transcript. Adds on-screen text (OCR), timed segments and the opening hook.
You can access the TikTok & YouTube Transcript API - Video to Text, Captions & OCR programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "EPKz2URKAGT9MyPqc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/headply~tiktok-youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-headply-tiktok-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/headply~tiktok-youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-headply-tiktok-youtube-transcript-scraper", "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/headply~tiktok-youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-headply-tiktok-youtube-transcript-scraper", "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": [ "startUrls" ], "properties": { "startUrls": { "title": "Video, channel or playlist URLs", "type": "array", "description": "TikTok video URLs (tiktok.com/@user/video/...), YouTube video or Shorts URLs, or YouTube channel and playlist URLs (expanded to their recent videos).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxVideos": { "title": "Max videos", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper bound on how many videos to process, including videos expanded from a channel or playlist URL.", "default": 100 }, "transcriptSource": { "title": "Transcript source", "enum": [ "caption", "caption-and-speech" ], "type": "string", "description": "How the transcript is produced, which sets what you pay. <b>Captions only</b> (default) returns the platform's own caption track — cheapest and fastest; a video with no caption is skipped and not charged. <b>Captions + speech recognition</b> additionally downloads the audio and transcribes it on-device for videos that have no caption; this costs more and is billed as a separate, higher-priced <b>speech-recognition</b> event. Speech recognition and OCR are CPU-intensive; for videos beyond about a minute, raise the Actor's memory (4 GB works well) so the run finishes before the timeout. Captions need no extra memory.", "default": "caption" }, "includeOnScreenText": { "title": "Read on-screen text (OCR)", "type": "boolean", "description": "Recognize the text burned into the video frames (titles, captions, callouts) with OCR — text no caption track carries. This downloads the video and runs image recognition, so it is the most expensive option and is billed as a separate <b>on-screen-text</b> event, on top of the transcript. Leave off unless you need it. Speech recognition and OCR are CPU-intensive; for videos beyond about a minute, raise the Actor's memory (4 GB works well) so the run finishes before the timeout. Captions need no extra memory.", "default": false }, "language": { "title": "Preferred language", "type": "string", "description": "Two-letter language code for the transcript, for example <b>en</b>. Leave empty to auto-detect and use the video's own caption language." }, "hookSeconds": { "title": "Hook length", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many opening seconds to pull into a separate hook field, which is what creative teams sort on.", "default": 5 }, "ocrFrameInterval": { "title": "On-screen text: frame interval", "minimum": 1, "maximum": 15, "type": "integer", "description": "Seconds between sampled frames when reading on-screen text. Lower catches more text but costs more.", "default": 3 }, "ocrMaxFrames": { "title": "On-screen text: max frames", "minimum": 1, "maximum": 200, "type": "integer", "description": "Safety cap on frames read per video.", "default": 10 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 12, "type": "integer", "description": "How many videos to fetch in parallel.", "default": 4 }, "maxDurationSecs": { "title": "Max duration for speech recognition / OCR", "minimum": 0, "type": "integer", "description": "Skip the costly paths (speech recognition and on-screen-text OCR) for videos longer than this many seconds. The caption is still returned when one exists. This protects against a single long video running up a large download and compute bill, which for speech recognition and OCR grows with video length. Set 0 to disable the cap.", "default": 600 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for TikTok & YouTube Transcript API - Video to Text, Captions & OCR from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients:
TikTok & YouTube Transcript API - Video to Text, Captions & OCR API in Python
TikTok & YouTube Transcript API - Video to Text, Captions & OCR API in JavaScript
TikTok & YouTube Transcript API - Video to Text, Captions & OCR API through CLI
TikTok & YouTube Transcript API - Video to Text, Captions & OCR API