# Twitter Video Transcript API – AI Video to Text for X (Twitter) (`apple_yang/twitter-video-transcript-api`) Actor Twitter Video Transcript API for converting video audio into accurate text using AI. Extract transcripts, spoken content, and metadata from X (Twitter) videos, tweets, and threads. Fast, reliable, and built for developers, AI agents, and automation workflows. - **URL**: https://apify.com/apple\_yang/twitter-video-transcript-api.md - **Developed by:** [APISmith](https://apify.com/apple_yang) (community) - **Categories:** Social media, Videos, AI - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $1.00 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Twitter Video Transcript API – AI Video to Text for X (Twitter) Convert **X (Twitter) video audio into accurate text** using AI. Extract transcripts, spoken content, and metadata from videos, tweets, and threads. Fast, reliable, and built for developers, AI agents, and automation workflows. --- ### What does Twitter Video Transcript API do? Twitter Video Transcript API uses advanced AI to **transcribe spoken audio from X (Twitter) videos into accurate text**. Provide a video URL, get back: - 📝 **AI-generated transcript** — word-by-word transcription with precise timestamps - ⏱️ **Segmented timing** — time ranges for each speech segment - 📊 **Full metadata** — tweet content, engagement stats, author info, video details - ⚡ **Instant results** — transcription completes in seconds Perfect for **AI training data collection**, **content analysis pipelines**, **social listening**, and **automation workflows** that need reliable access to Twitter video transcripts. --- ### What can this API extract? | Field | Type | Description | |-------|------|-------------| | `url` | string | Original X (Twitter) post URL | | `title` | string | Tweet text/content | | `createTime` | number | Unix timestamp of tweet creation | | `img` | string | Thumbnail image URL | | `videoUrl` | string | Direct MP4 video download link | | `bookmarkCount` | number | Number of bookmarks | | `favoriteCount` | number | Number of likes | | `quoteCount` | number | Number of quotes | | `replyCount` | number | Number of replies | | `retweetCount` | number | Number of retweets | | `nickname` | string | Author's display name | | `screenName` | string | Author's username | | `avatarUri` | string | Author's profile picture URL | | `authorDesc` | string | Author's bio/description | | `authorFavouritesCount` | number | Author's total likes | | `authorFollowersCount` | number | Author's follower count | | `authorFriendsCount` | number | Author's following count | | `authorListedCount` | number | Author's list count | | `authorMediaCount` | number | Author's media count | | `authorStatusesCount` | number | Author's tweet count | | `duration` | number | Video duration in seconds | | `text` | string | Complete AI transcript text | | `segments` | array | Transcript segments with timestamps | | `timestamp` | string | ISO 8601 timestamp of extraction | | `errMsg` | string | Error message (if any) | --- ### Our Video Downloader & Transcript Suite Need to extract videos or transcripts from other platforms? Check out our complete collection: | Platform | Video Downloader | Transcript Extractor | |----------|-----------------|---------------------| | **TikTok** | [TikTok Video Downloader](https://apify.com/apple_yang/tiktok-video-audio-downloader) | [TikTok Transcript Extractor](https://apify.com/apple_yang/tiktok-transcripts-scraper) | | **Instagram** | [Instagram Video Scraper API](https://apify.com/apple_yang/instagram-video-scraper-api) | [Instagram Transcript Extractor](https://apify.com/apple_yang/instagram-transcripts-scraper) | | **X (Twitter)** | [X Video Downloader](https://apify.com/apple_yang/twitter-video-scraper-api) | [X Transcript Extractor](https://apify.com/apple_yang/twitter-video-transcript-api) ⭐ | | **Facebook** | [Facebook Video Downloader](https://apify.com/apple_yang/facebook-video-audio-downloader) | [Facebook Transcript Extractor](https://apify.com/apple_yang/facebook-transcript-scraper-api) | | **Douyin** | [Douyin Video Downloader](https://apify.com/apple_yang/douyin-video-audio-downloader) | [Douyin Transcript Extractor](https://apify.com/apple_yang/douyin-transcripts-scraper) | | **Bilibili** | [Bilibili Video Downloader](https://apify.com/apple_yang/bilibili-video-audio-downloader) | [Bilibili Transcript Extractor](https://apify.com/apple_yang/bilibili-transcripts-scraper) | #### 🌟 Special Offerings - **[High Accuracy Douyin Transcripts Scraper](https://apify.com/apple_yang/douyin-transcripts-scraper)** — Premium quality transcription specifically optimized for Douyin (抖音) content with enhanced accuracy for Mandarin speech. --- ### Quick Start #### Option 1: No-Code (Apify Console) The easiest way to get started without writing any code: 1. **Sign up** for a free Apify account at [console.apify.com](https://console.apify.com/sign-up) 2. **Open** [Twitter Video Transcript API](https://apify.com/apple_yang/twitter-video-transcript-api) 3. **Paste** your X (Twitter) video URL in the input field 4. **Click** the "Start" button to run the transcript extraction 5. **Download** your results in JSON, CSV, or Excel format from the Storage tab #### Option 2: API Integration For developers who want to integrate into their applications: ##### 1. Get your API token Sign up at [Apify Console](https://console.apify.com/sign-up) and copy your API token from the [Integrations](https://console.apify.com/account#/integrations) page. ##### 2. Make a request **cURL:** ```bash curl -X POST 'https://api.apify.com/v2/acts/apple_yang/twitter-video-transcript-api/runs?token=YOUR_TOKEN' \ -H 'Content-Type: application/json' \ -d '{ "videoUrl": "https://x.com/i/status/2040031089696162156" }' ```` **JavaScript:** ```javascript const { ApifyClient } = require('apify-client'); const client = new ApifyClient({ token: 'YOUR_TOKEN' }); const run = await client.actor('apple_yang/twitter-video-transcript-api').call({ videoUrl: 'https://x.com/i/status/2040031089696162156' }); const { items } = await client.dataset(run.defaultDatasetId).listItems(); console.log(items[0].text); // Complete transcript ``` **Python:** ```python from apify_client import ApifyClient client = ApifyClient('YOUR_TOKEN') run = client.actor('apple_yang/twitter-video-transcript-api').call( run_input={'videoUrl': 'https://x.com/i/status/2040031089696162156'} ) for item in client.dataset(run['defaultDatasetId']).iterate_items(): print(item['text']) ## Complete transcript ``` ##### 3. Download your data Retrieve results via API or download from the [Apify Console](https://console.apify.com/storage) in JSON, CSV, or Excel format. *** ### Input | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `videoUrl` | string | ✅ Yes | X (Twitter) video URL to transcribe | #### Input example ```json { "videoUrl": "https://x.com/i/status/2040031089696162156" } ``` *** ### Output Results are returned as a JSON array. Download via API or export as JSON, CSV, or Excel. #### Output example ```json [ { "url": "https://x.com/i/status/2040031089696162156", "title": "People don't read.\n\nThey scan.\n\nMost people scan in what's call an 'F' shape pattern.\n\nYour eyes go from 1 to 2 to 3 to 4 to 5.\n\nAnd, words don't have to be spelled in the correct order for your brain to know what it is.\n\nThat's because you don't read them.\n\nYou can scan them. https://t.co/mStX7IIGgz", "createTime": 1775216288, "img": "https://pbs.twimg.com/ext_tw_video_thumb/2040031059455123456/pu/img/eATQIrbhqR-OU2Yi.jpg", "videoUrl": "https://video.twimg.com/ext_tw_video/2040031059455123456/pu/vid/avc1/720x1280/KdRUI2A40sbho_h_.mp4?tag=12", "bookmarkCount": 0, "favoriteCount": 0, "quoteCount": 0, "replyCount": 0, "retweetCount": 0, "nickname": "Growth Hackers 🚀", "screenName": "StartGrowthHack", "avatarUri": "https://pbs.twimg.com/profile_images/1303560724988395520/FT9pk2Om_normal.jpg", "authorDesc": "Grow your business with https://t.co/S7ETrP8icC\nAward-Winning Growth Hacking Agency | Lead Generation | Customer Acquisition | AI-Powered Digital Marketing", "authorFavouritesCount": 65099, "authorFollowersCount": 171030, "authorFriendsCount": 12841, "authorListedCount": 2446, "authorMediaCount": 30521, "authorStatusesCount": 171928, "duration": 21.461333, "text": "People don't read, they scan. Most people scan in what's called an F-shaped pattern. Your eyes go from 1 to 2 to 3 to 4 to 5. And words don't have to be spelled in the correct order for your brain to know what it is. That's because you don't read them, you scan them. So if you're making a website, make it scannable. If you're running ads, make them scannable because...", "segments": [ { "start": 0, "end": 1.78, "text": "People don't read, they scan." }, { "start": 2, "end": 4.9, "text": "Most people scan in what's called an F-shaped pattern." }, { "start": 5.22, "end": 8.16, "text": "Your eyes go from 1 to 2 to 3 to 4 to 5." }, { "start": 8.38, "end": 12.54, "text": "And words don't have to be spelled in the correct order for your brain to know what it is." }, { "start": 12.7, "end": 15.14, "text": "That's because you don't read them, you scan them." }, { "start": 15.32, "end": 18.02, "text": "So if you're making a website, make it scannable." }, { "start": 18.2, "end": 21.28, "text": "If you're running ads, make them scannable because..." } ], "errMsg": "", "timestamp": "2026-04-04T02:04:30.980Z" } ] ``` *** ### How much does it cost? **Two-part pricing** — pay for data extraction + AI transcription separately. #### Part 1: Data Extraction (Fixed Rate) Extract video metadata, author info, and engagement data from X (Twitter). | Component | Price | |-----------|-------| | Per result | **$0.001** | | Per 1,000 results | **$1.00** | > 💡 **Note:** This fee applies to every video processed, regardless of duration. #### Part 2: AI Transcription (Tier-Based) Convert video audio to text. Pricing varies by your Apify plan tier. | Apify Tier | Price per Minute | Discount | Best For | |-----------|-----------------|----------|----------| | **Free** | $0.0025 | — | Testing, small projects | | **Starter** | $0.0020 | Bronze | Individual developers | | **Scale** | $0.0015 | Silver | Growing teams | | **Business** | $0.0010 | Gold | High-volume operations | #### Billing Rules | Rule | Description | |------|-------------| | **Duration rounding** | Charged per minute, rounded up (e.g., 1.5 min = 2 min) | | **Minimum charge** | Videos under 1 minute billed as 1 minute | | **No audio, no charge** | Videos without audio tracks are not charged for transcription | | **AI processing fee applies** | Videos with audio are charged even if no speech is detected, because AI compute resources are still required to analyze and verify the absence of speech | | **Free plan credits** | Includes $5/month in compute credits. At a rate of $0.0025 per minute, this covers up to ~2,000 minutes of video transcription per month (actual usage depends on rounding rules) | #### Cost Example Processing **1,000 videos** (1 minute each): | Cost Component | Free Tier | Business Tier | |----------------|-----------|---------------| | Data extraction (1,000 results) | $1.00 | $1.00 | | AI transcription (1,000 min) | $2.50 | $1.00 | | **Total** | **$3.50** | **$2.00** | *** ### Use cases #### 🤖 AI & Machine Learning - Build speech recognition models - Train NLP systems on social media content - Create multimodal datasets with video + transcript #### 📊 Social Listening - Monitor brand mentions and sentiment - Track trending topics and discussions - Analyze competitor content strategies #### 📈 Content Analysis - Extract insights from viral videos - Identify key messaging patterns - Build recommendation engines #### 🔄 Automation Pipelines - Auto-transcribe creator content - Archive tweet videos with full text - Feed transcribed data into content management systems #### 🎯 Research & Analytics - Academic research on social media discourse - Market research based on video content - Journalism and news gathering *** ### Important notes #### Video requirements - **Public content only:** This API only works with publicly accessible X (Twitter) videos. Private tweets and protected accounts cannot be accessed. - **Speech required:** Videos without spoken audio will return metadata but no transcript. - **Duration limits:** Long videos may take additional processing time. #### Transcript accuracy AI transcription accuracy typically exceeds **95%** for clear speech with good audio quality. Accuracy may vary based on: - Background noise and music - Multiple speakers or overlapping speech - Accents and dialects - Audio quality and bit rate #### Rate limiting Requests are processed through Apify's infrastructure with built-in resource management. Large batches may take longer to complete. *** ### FAQ #### Is it legal to transcribe X (Twitter) videos? This API only transcribes **publicly available content** that users have chosen to share openly. We do not access private content or personal data. However, you should be aware that: - Results may contain personal data protected by GDPR and other regulations - You should only transcribe data you have a legitimate reason to use - Transcribed content should be used in compliance with copyright and platform policies - When in doubt, consult legal counsel Read more about [web scraping legality](https://blog.apify.com/web-scraping-legal/). #### What happens if a video has no speech? If a video contains only music, sound effects, or no detectable speech, the API will return all metadata but the `text` and `segments` fields will be empty or minimal. #### Can I transcribe threads? Currently, this API processes individual video URLs. For threads with multiple videos, submit each video URL separately. #### Do you support X (Twitter) Spaces audio? This API is designed for video content. Spaces audio is not currently supported. #### How long does transcription take? Most videos are transcribed within **5-30 seconds**, depending on duration. Shorter videos (< 1 minute) typically complete in under 10 seconds. #### Do you offer custom solutions? For high-volume needs, custom features, or enterprise integrations, contact us to discuss tailored solutions. *** ### Support We're committed to making your experience smooth and productive. Whether you're just getting started or running large-scale operations, we're here to help: #### Get in touch for anything: - 🐛 **Found a bug?** — Let us know what went wrong and we'll fix it quickly - 💡 **Need a feature?** — Tell us what would make your workflow better - ❓ **Have questions?** — Stuck on something? Ask us anything about using the API - 🚀 **Hit a limitation?** — If our current setup doesn't quite fit your needs, let's talk - 🏢 **Enterprise needs?** — High-volume requirements, custom integrations, or tailored solutions — we can build it 📧 **Contact us:** [support@transcript365.com](mailto:support@apismith.online) We read every email and typically respond within 24 hours. Don't hesitate to reach out — your feedback helps us improve! *** *Built for developers who need reliable X (Twitter) video transcription without complexity.* # Actor input Schema ## `videoUrl` (type: `string`): The URL of the twitter you want to get the data from. ## Actor input object example ```json { "videoUrl": "https://x.com/Dell_JPN/status/1975063471155970378" } ``` # Actor output Schema ## `results` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "videoUrl": "https://x.com/Dell_JPN/status/1975063471155970378" }; // Run the Actor and wait for it to finish const run = await client.actor("apple_yang/twitter-video-transcript-api").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "videoUrl": "https://x.com/Dell_JPN/status/1975063471155970378" } # Run the Actor and wait for it to finish run = client.actor("apple_yang/twitter-video-transcript-api").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "videoUrl": "https://x.com/Dell_JPN/status/1975063471155970378" }' | apify call apple_yang/twitter-video-transcript-api --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=apple_yang/twitter-video-transcript-api", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Twitter Video Transcript API – AI Video to Text for X (Twitter)", "description": "Twitter Video Transcript API for converting video audio into accurate text using AI. Extract transcripts, spoken content, and metadata from X (Twitter) videos, tweets, and threads. Fast, reliable, and built for developers, AI agents, and automation workflows.", "version": "0.0", "x-build-id": "Bfo8hdBMc0ouzeqT1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/apple_yang~twitter-video-transcript-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-apple_yang-twitter-video-transcript-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/apple_yang~twitter-video-transcript-api/runs": { "post": { "operationId": "runs-sync-apple_yang-twitter-video-transcript-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/apple_yang~twitter-video-transcript-api/run-sync": { "post": { "operationId": "run-sync-apple_yang-twitter-video-transcript-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "videoUrl" ], "properties": { "videoUrl": { "title": "The URL of the twitter", "type": "string", "description": "The URL of the twitter you want to get the data from." } } }, "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 } } }, "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 } } } } } } } } } } ```