# VidCrawl Complete Agent Documentation > Turn YouTube, TikTok, Instagram Reels, and X video URLs into LLM-ready timestamped Markdown, visual storyboard frames, on-screen OCR, and structured JSON via remote MCP, stdio MCP, CLI, or REST API. Base URL: https://vidcrawl.com OpenAPI 3.1: https://vidcrawl.com/docs/json Skill File: https://vidcrawl.com/skill.md Remote MCP: https://vidcrawl.com/mcp --- # VidCrawl VidCrawl gives AI agents structured video context from public YouTube (including Shorts), TikTok, Instagram Reels, and X video URLs. ## Progressive Disclosure Rules 1. Always start with Layer 1 (`vidcrawl_scrape` or `POST /v1/scrape`, 1 credit, 0 LLM tokens). It returns metadata, chapters, deduplicated timestamped transcript segments, a lightweight storyboard grid, and LLM-ready Markdown. 2. Never ingest a full raw video stream into a language model by default. 3. Use Layer 2A (`vidcrawl_frames` or `POST /v1/frames`, 1 credit) only when the transcript and storyboard leave ambiguity on a specific slide, code block, chart, or UI screen. Pass exact `timestamps_sec` (1 to 20 timestamps, `max_width` 320 to 1920). 4. Use Layer 2B (`vidcrawl_search` or `POST /v1/search`, 1 credit) to discover YouTube videos by topic, optionally setting `scrape: true` (+1 credit per scraped result). 5. Use Layer 3 (`vidcrawl_agent` or `POST /v1/agent`, 3/5/10 credits for `low`/`medium`/`high` effort) for bounded multi-step visual + spoken synthesis across 1 to 10 URLs with `[MM:SS]` citations and optional JSON `schema`. 6. Use `vidcrawl_account` or `GET /v1/account` (0 credits) to verify authentication and inspect remaining credits before batch runs. 7. Always cite `[MM:SS]` timestamps in your answers and distinguish spoken evidence from visual evidence. ## Remote Streamable HTTP MCP Setup Endpoint: `https://vidcrawl.com/mcp` (also mounted at `https://vidcrawl.com/v1/mcp`). Authenticate with `Authorization: Bearer $VIDCRAWL_API_KEY` or `x-api-key: $VIDCRAWL_API_KEY`. ### Claude Code ```bash claude mcp add --transport http vidcrawl https://vidcrawl.com/mcp \ --header "Authorization: Bearer $VIDCRAWL_API_KEY" ``` ### OpenAI Codex ```bash codex mcp add vidcrawl --url https://vidcrawl.com/mcp # In ~/.codex/config.toml under [mcp_servers.vidcrawl], set: # bearer_token_env_var = "VIDCRAWL_API_KEY" ``` ### Cursor / Windsurf / VS Code Add to your MCP JSON configuration (`.cursor/mcp.json` or `~/.cursor/mcp.json`): ```json { "mcpServers": { "vidcrawl": { "url": "https://vidcrawl.com/mcp", "headers": { "Authorization": "Bearer $VIDCRAWL_API_KEY" } } } } ``` ## Local Stdio MCP and CLI Run the stdio MCP server or CLI with `VIDCRAWL_API_KEY` set (pointing to `https://vidcrawl.com`): ```bash # Stdio MCP server VIDCRAWL_API_KEY="$VIDCRAWL_API_KEY" VIDCRAWL_API_URL="https://vidcrawl.com" npx -y @vidcrawl/mcp mcp # CLI commands npx -y @vidcrawl/mcp scrape 'https://www.youtube.com/watch?v=1E3tv_3D95g' npx -y @vidcrawl/mcp frames 'https://www.youtube.com/watch?v=1E3tv_3D95g' --at 150,365 npx -y @vidcrawl/mcp search 'MiniMax AI lab' --limit 5 npx -y @vidcrawl/mcp agent 'https://www.youtube.com/watch?v=1E3tv_3D95g' --prompt 'Summarize key changes' --effort low ``` ## MCP Tools - `vidcrawl_scrape` (1 credit): Extract metadata, chapters, timestamped transcript, storyboard sheets, and Markdown. Input: `{ url, lang? }`. - `vidcrawl_frames` (1 credit): Extract up to 20 high-resolution JPEG frames at `timestamps_sec`. Input: `{ url, timestamps_sec, max_width? }`. - `vidcrawl_search` (1 credit, +1 per scraped result): Search YouTube videos. Input: `{ query, limit?, scrape?, lang? }`. - `vidcrawl_agent` (3/5/10 credits): Grounded video agent across 1 to 10 URLs. Input: `{ prompt, urls, effort?, schema? }`. - `vidcrawl_account` (0 credits): Check remaining credit balance and endpoint credit prices. Input: `{}`. ## REST API Reference Base URL: `https://vidcrawl.com` Authentication header: `Authorization: Bearer ` or `x-api-key: `. - `POST /v1/scrape` (1 credit): Body `{ "url": "...", "formats"?: ["markdown", "segments", "storyboard"], "lang"?: "en" }` - `POST /v1/frames` (1 credit): Body `{ "url": "...", "timestamps_sec": [150, 365], "max_width"?: 1280 }` - `POST /v1/search` (1 credit): Body `{ "query": "...", "platform"?: "youtube", "limit"?: 5, "scrape"?: false, "lang"?: "en" }` - `POST /v1/agent` (3/5/10 credits): Body `{ "prompt": "...", "urls": ["..."], "effort"?: "low" | "medium" | "high", "schema"?: { ... } }` - `GET /v1/account` (0 credits): Returns `{ ok: true, user_id, credits, costs }`. ## Credits and Packs - New accounts start with 100 free credits (no card required). - Starter Pack: 1,000 credits for $9 (one-time, never expire). - Growth Pack: 4,000 credits for $29 (one-time, never expire). ## Error Codes Every error returns JSON `{ "ok": false, "error": { "code": "...", "message": "...", "request_id": "..." } }` and sets the `X-Request-Id` header. - `UNAUTHORIZED` (401): Missing or invalid API key. - `INSUFFICIENT_CREDITS` (402): Balance is below the required endpoint credits. - `INVALID_JSON` (400): Request body is not valid JSON. - `VALIDATION_ERROR` (400): Request fields failed contract validation (see `error.issues`). - `PAYLOAD_TOO_LARGE` (413): Request body exceeded 65536 bytes. - `INVALID_URL` / `UNSUPPORTED_PLATFORM`: URL is not a supported public YouTube, TikTok, Instagram Reel, or X video (or search on an unsupported platform). - `VIDEO_UNAVAILABLE` (404): Video is private, deleted, or region-restricted. - `NO_CAPTIONS_AVAILABLE`: No captions or spoken transcript could be extracted. - `MEDIA_UNAVAILABLE`: Video media stream could not be accessed for frame slicing. - `YOUTUBE_BOT_CHALLENGED`: Upstream provider challenged the request; retry later. - `UPSTREAM_TIMEOUT` / `UPSTREAM_ERROR` (500/502): Upstream extraction or model failure. ## Discovery Links - OpenAPI 3.1 JSON: `https://vidcrawl.com/docs/json` - Interactive API Reference: `https://vidcrawl.com/api-reference` - Markdown API Reference: `https://vidcrawl.com/api-reference.md` - MCP Setup Guide: `https://vidcrawl.com/mcp` (`https://vidcrawl.com/mcp.md`) - Compact Index: `https://vidcrawl.com/llms.txt` - Complete Bundle: `https://vidcrawl.com/llms-full.txt` --- # VidCrawl API Reference Canonical HTML UI: https://vidcrawl.com/api-reference OpenAPI 3.1 JSON: https://vidcrawl.com/docs/json Canonical Agent Skill: https://vidcrawl.com/skill.md Remote MCP Endpoint: https://vidcrawl.com/mcp ## Base URL and Authentication - Base URL: `https://vidcrawl.com` - Authenticate with `Authorization: Bearer ` or `x-api-key: `. - Do not send conflicting values across both headers. - Request body size limit: 65536 bytes. - Response headers: `X-Request-Id`, `X-Credits-Used`, `X-Credits-Remaining`, and `X-Cache` (`HIT` or `MISS` on `/v1/scrape`). ## Pricing and Credits - New accounts receive 100 free credits. - Starter Pack: 1,000 credits for $9 (never expire). - Growth Pack: 4,000 credits for $29 (never expire). - Failed requests caused by invalid input, missing credits, or upstream unavailability before model completion do not deduct credits. ## Endpoints ### POST /v1/scrape (1 credit) Deterministic Layer 1 extraction (0 LLM tokens). Returns metadata, chapters, outgoing description links, deduplicated timestamped transcript segments, storyboard sheets, and Markdown. Request body: ```json { "url": "https://www.youtube.com/watch?v=1E3tv_3D95g", "formats": ["markdown", "segments", "storyboard"], "lang": "en" } ``` - `url` (required): Public YouTube (including Shorts), TikTok, Instagram Reel, or X video URL. - `formats` (optional): Non-empty unique subset of `["markdown", "segments", "storyboard"]`. Defaults to all three. - `lang` (optional): BCP 47 language tag (max 16 chars), default `"en"`. ### POST /v1/frames (1 credit) Targeted Layer 2A visual inspection. Extracts 1 to 20 JPEG frames at exact `timestamps_sec`. Request body: ```json { "url": "https://www.youtube.com/watch?v=1E3tv_3D95g", "timestamps_sec": [150, 365], "max_width": 1280 } ``` - `url` (required): Supported public video URL. - `timestamps_sec` (required): 1 to 20 non-negative numbers in seconds. - `max_width` (optional): Integer from 320 to 1920, default 1280. ### POST /v1/search (1 credit) Layer 2B video discovery on YouTube with optional full Layer 1 scrape enrichment. Request body: ```json { "query": "MiniMax Chinese AI Lab Scottish Mortgage", "platform": "youtube", "limit": 5, "scrape": false, "lang": "en" } ``` - `query` (required): Non-empty search string (max 200 chars). - `platform` (optional): `"youtube"` (default). `"tiktok"` returns `UNSUPPORTED_PLATFORM`. - `limit` (optional): Integer 1 to 20, default 5. - `scrape` (optional): Boolean, default `false`. When `true`, charges +1 credit per successfully scraped result. ### POST /v1/agent (3 / 5 / 10 credits) Layer 3 bounded progressive-disclosure video agent. Scrapes context first, inspects storyboard sheets and sharp frames as needed, and returns grounded answers with `[MM:SS]` citations and optional structured JSON. Request body: ```json { "prompt": "What does Liquid Glass change in iOS 26, and what concerns does the reviewer raise?", "urls": ["https://www.youtube.com/watch?v=1E3tv_3D95g"], "effort": "low", "schema": { "type": "object", "properties": { "highlights": { "type": "array", "items": { "type": "string" } } } } } ``` - `prompt` (required): Non-empty string, max 4000 chars. - `urls` (required): 1 to 10 supported public video URLs. - `effort` (optional): `"low"` (3 credits, default), `"medium"` (5 credits), or `"high"` (10 credits). - `schema` (optional): JSON object up to 8192 serialized bytes. ### GET /v1/account (0 credits) Check authenticated user ID, remaining credits, and current per-endpoint credit costs. ### POST /mcp and GET /mcp Remote Streamable HTTP JSON-RPC 2.0 MCP server (also available at `https://vidcrawl.com/v1/mcp`). Exposes `vidcrawl_scrape`, `vidcrawl_frames`, `vidcrawl_search`, `vidcrawl_agent`, and `vidcrawl_account`. ### GET /healthz (0 credits, unauthenticated) Service liveness check returning `{ "ok": true, "service": "vidcrawl-api", "version": "0.1.0" }`. ## Error Codes All errors follow `{ "ok": false, "error": { "code": "...", "message": "...", "request_id": "..." } }`: - `UNAUTHORIZED` - `INSUFFICIENT_CREDITS` - `INVALID_JSON` - `PAYLOAD_TOO_LARGE` - `NOT_FOUND` - `YOUTUBE_BOT_CHALLENGED` - `VIDEO_UNAVAILABLE` - `NO_CAPTIONS_AVAILABLE` - `INVALID_URL` - `UNSUPPORTED_PLATFORM` - `UPSTREAM_ERROR` - `UPSTREAM_TIMEOUT` - `MEDIA_UNAVAILABLE` - `VALIDATION_ERROR` --- # VidCrawl MCP Server Canonical URL: https://vidcrawl.com/mcp Remote Endpoint: https://vidcrawl.com/mcp (and https://vidcrawl.com/v1/mcp) Agent Skill: https://vidcrawl.com/skill.md Connect VidCrawl directly to Claude Code, OpenAI Codex, Cursor, Windsurf, or any MCP-compatible coding or research agent. ## Prompt for Your AI Agent ```text Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify. ``` ## Quick Setup ### Claude Code (Remote HTTP) ```bash claude mcp add --transport http vidcrawl https://vidcrawl.com/mcp \ --header "Authorization: Bearer $VIDCRAWL_API_KEY" ``` ### OpenAI Codex ```bash codex mcp add vidcrawl --url https://vidcrawl.com/mcp # Set bearer_token_env_var = "VIDCRAWL_API_KEY" under [mcp_servers.vidcrawl] in ~/.codex/config.toml ``` ### Cursor / Windsurf / VS Code ```json { "mcpServers": { "vidcrawl": { "url": "https://vidcrawl.com/mcp", "headers": { "Authorization": "Bearer YOUR_VIDCRAWL_API_KEY" } } } } ``` ### Local Stdio (npx) ```bash claude mcp add vidcrawl \ -e VIDCRAWL_API_KEY="$VIDCRAWL_API_KEY" \ -e VIDCRAWL_API_URL="https://vidcrawl.com" \ -- npx -y @vidcrawl/mcp mcp ``` ## Available MCP Tools (5) | Tool | Purpose | Credits | |---|---|---| | `vidcrawl_scrape` | Extract metadata, chapters, timestamped transcript, storyboard sheets, and Markdown | 1 credit | | `vidcrawl_frames` | Slice 1 to 20 high-resolution JPEG frames at exact timestamps (320 to 1920px) | 1 credit | | `vidcrawl_search` | Search YouTube videos with optional full scrape enrichment | 1 credit (+1 per scraped result) | | `vidcrawl_agent` | Grounded video agent across 1 to 10 URLs with [MM:SS] citations and JSON schema | 3 / 5 / 10 credits (low/medium/high) | | `vidcrawl_account` | Check remaining credit balance and per-endpoint credit prices | 0 credits | ## Example Agent Prompts 1. "Read https://www.youtube.com/watch?v=1E3tv_3D95g with VidCrawl, inspect sharp frames where UI changes appear, and summarize the takeaways with [MM:SS] timestamps." 2. "Search YouTube for 'MiniMax AI lab' using vidcrawl_search, scrape the top 3 results, and summarize the main technical points." 3. "Use vidcrawl_agent on this tutorial video with a JSON schema listing every CLI command shown on screen and its timestamp." 4. "Call vidcrawl_account to verify my remaining VidCrawl credit balance." --- # Turn any video into context your agent can read > Turn YouTube, TikTok, Instagram Reels, and X videos into timestamped transcripts, storyboards, and sharp frames. One API, Markdown and JSON out, built for AI agents. Canonical URL: https://vidcrawl.com/ Markdown URL: https://vidcrawl.com/index.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp Timestamped transcripts, storyboards, and sharp frames from YouTube, TikTok, Instagram Reels, and X. One API, Markdown and JSON out. ## Endpoints - `POST /v1/scrape` (1 credit): Metadata, chapters, timestamped transcript, storyboard sheets, and Markdown. - `POST /v1/frames` (1 credit): Up to 20 high-resolution JPEG frames at chosen timestamps. - `POST /v1/search` (1 credit): Search YouTube videos with optional scrape enrichment. - `POST /v1/agent` (3/5/10 credits): Bounded video agent with [MM:SS] citations and optional JSON schema. - `GET /v1/account` (0 credits): Check remaining credits and endpoint prices. - `POST /mcp`: Remote Streamable HTTP MCP server. ## Pricing - 100 free credits on signup (no card required). - Starter Pack: 1,000 credits for $9 (credits never expire). - Growth Pack: 4,000 credits for $29 (credits never expire). ## Frequently Asked Questions ### Which platforms are supported? Public videos on YouTube (including Shorts), TikTok, Instagram Reels, and X. Private, age-restricted, or deleted videos return a clear error instead of partial data. ### What if a video has no captions? VidCrawl transcribes the speech with timestamps. For long videos without captions, only the first part is transcribed and the response says how much was covered. ### Why not send the whole video to a multimodal model? A long video costs a lot of tokens and is slow. Starting from text and small storyboard images, then requesting sharp frames only where needed, keeps agents fast and cheap. ### Does VidCrawl use an LLM to produce the transcript? No. /v1/scrape and /v1/frames are deterministic. Only /v1/agent calls a model, and you choose when to use it. ### Do I need an account to try it? No. The playground at the top of this page reads any public video for free, with a daily limit. Sharp frames, questions, and the API need a free account, which comes with 100 credits. ### How do agents discover the API? The full API is described in /llms.txt and as an OpenAPI 3.1 spec, so coding agents can read it and call the endpoints without a custom SDK. --- # YouTube transcript generator > Paste a YouTube link and get the full transcript with timestamps, chapters, and a storyboard of the video. Copy it or export Markdown, SRT, plain text, or JSON. Free, no account. Canonical URL: https://vidcrawl.com/youtube-transcript Markdown URL: https://vidcrawl.com/youtube-transcript.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp Paste a YouTube link to get the full transcript with timestamps, organised by chapter, next to a storyboard of the video. Free, no account. ## What You Get ### The full transcript, with timestamps Creator captions when they exist, auto captions otherwise, with duplicated lines removed and every sentence tied to its moment. ### Chapters and a storyboard The transcript is grouped by the creator's chapters, with a frame every ten seconds so you can see what was on screen. ### Four export formats Markdown for notes and prompts, SRT for subtitles, plain text for reading, and JSON for code. ## Need transcripts in your app? The same result is one POST away. One credit per video, Markdown and JSON in the response. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.youtube.com/watch?v=1E3tv_3D95g"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### Is the YouTube transcript generator free? Yes. Reading a video in the browser is free and needs no account. There is a daily limit; a free account adds 100 credits for the API and for sharp frames. ### Can I download the transcript? Yes. Copy it, or download it as Markdown, SRT subtitles, plain text, or JSON. The SRT keeps every timestamp. ### Does it work on videos without captions? Yes. When a video has no captions, VidCrawl transcribes the speech. On long videos without captions only the first part is transcribed, and the result says how much was covered. ### Does it work with YouTube Shorts? Yes. Paste the Shorts link the same way. Shorts return the transcript and a storyboard. ### What are the pictures next to the transcript? They are the video's storyboard: one small frame roughly every ten seconds. Click any frame or any sentence to jump to that moment. ## Related Pages - [YouTube transcript API](https://vidcrawl.com/youtube-transcript-api) ([Markdown](https://vidcrawl.com/youtube-transcript-api.md)) - [Video to Markdown](https://vidcrawl.com/video-to-markdown) ([Markdown](https://vidcrawl.com/video-to-markdown.md)) - [TikTok transcript](https://vidcrawl.com/tiktok-transcript) ([Markdown](https://vidcrawl.com/tiktok-transcript.md)) - [Instagram Reel transcript](https://vidcrawl.com/instagram-transcript) ([Markdown](https://vidcrawl.com/instagram-transcript.md)) --- # TikTok transcript generator > Paste a TikTok link and get what was said, with timestamps, plus a contact sheet of the clip. Copy the text or export Markdown, SRT, or JSON. Free, no account. Canonical URL: https://vidcrawl.com/tiktok-transcript Markdown URL: https://vidcrawl.com/tiktok-transcript.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp Paste a TikTok link to get what was said, with timestamps, next to a contact sheet of the clip. Free, no account. ## What You Get ### What was said, with timestamps The video's own captions when it has them, speech-to-text when it does not. ### A contact sheet of the clip Nine frames across the video, so the text comes with what was on screen. ### The post, too Author, caption, hashtags, and duration come back with the transcript. ## Reading TikTok at scale? The same result is one POST away, with the same response shape as YouTube. One credit per video. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.tiktok.com/@neildegrassetyson/video/7482856405934918955"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### How do I get a transcript of a TikTok video? Copy the video's link from the TikTok app or site, paste it above, and press Read video. The transcript appears with a timestamp on every line. ### What if the TikTok has no captions? VidCrawl uses the video's captions when it has them and transcribes the speech when it does not. Clips with only music return little or no text. ### What is the contact sheet? Nine frames spread across the clip, so you can see what happens in it without playing it. Click a frame to jump to that moment in the transcript. ### Can I download the TikTok transcript? Yes. Copy it, or download it as Markdown, SRT subtitles, plain text, or JSON. ### Which TikTok videos work? Public videos. Private accounts, deleted videos, and region-locked videos return a clear error. ## Related Pages - [TikTok transcript API](https://vidcrawl.com/tiktok-transcript-api) ([Markdown](https://vidcrawl.com/tiktok-transcript-api.md)) - [Instagram Reel transcript](https://vidcrawl.com/instagram-transcript) ([Markdown](https://vidcrawl.com/instagram-transcript.md)) - [YouTube transcript](https://vidcrawl.com/youtube-transcript) ([Markdown](https://vidcrawl.com/youtube-transcript.md)) - [Video to Markdown](https://vidcrawl.com/video-to-markdown) ([Markdown](https://vidcrawl.com/video-to-markdown.md)) --- # Instagram Reel transcript generator > Paste a public Instagram Reel link and get what was said, with timestamps, plus the post caption. Copy the text or export Markdown, SRT, or JSON. Free, no account. Canonical URL: https://vidcrawl.com/instagram-transcript Markdown URL: https://vidcrawl.com/instagram-transcript.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp Paste a public Reel link to get what was said, with timestamps, together with the post caption. Free, no account. ## What You Get ### What was said, with timestamps Speech transcribed from the Reel's audio, one timestamp per line. ### The post caption The caption and author come back with the transcript, so the text is never out of context. ### A clear answer when it cannot Private, deleted, or login-only Reels return a plain error, not half a transcript. ## Reading Reels at scale? The same result is one POST away, with the same response shape as YouTube and TikTok. One credit per video. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.instagram.com/reel/DX0P6QsPunU/"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### How do I get a transcript of an Instagram Reel? Open the Reel, copy its link from the share menu, paste it above, and press Read video. ### Which Reels work? Public Reels. Reels from private accounts, deleted Reels, and Reels that need a login cannot be read, and the tool says so instead of returning partial text. ### Where does the transcript come from? VidCrawl transcribes the speech in the Reel. Reels with only music return the post caption and little or no spoken text. ### Can I download the transcript? Yes. Copy it, or download it as Markdown, SRT subtitles, plain text, or JSON. ## Related Pages - [TikTok transcript](https://vidcrawl.com/tiktok-transcript) ([Markdown](https://vidcrawl.com/tiktok-transcript.md)) - [YouTube transcript](https://vidcrawl.com/youtube-transcript) ([Markdown](https://vidcrawl.com/youtube-transcript.md)) - [Video to Markdown](https://vidcrawl.com/video-to-markdown) ([Markdown](https://vidcrawl.com/video-to-markdown.md)) --- # YouTube transcript API > A YouTube transcript API that returns timestamped segments, chapters, description links, storyboard sheets, and Markdown in one POST. Sharp frames on request. 100 free credits. Canonical URL: https://vidcrawl.com/youtube-transcript-api Markdown URL: https://vidcrawl.com/youtube-transcript-api.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp One POST returns the transcript with timestamps, chapters, description links, storyboard sheets, and a Markdown document. No proxies or headless browsers to run. ## What You Get ### Segments your code can use Each segment has a start and end in seconds, a formatted timestamp, and clean text. ### Structure, not just words Title, author, duration, chapters, and the links from the description come back in the same response. ### Markdown for prompts A single Markdown document with front matter, chapters, and the transcript, ready to hand to a model. ## One request Authenticate with your API key and POST a video URL. One credit per video. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.youtube.com/watch?v=1E3tv_3D95g"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### What does the YouTube transcript API return? Metadata, chapters, timestamped transcript segments, the full text, storyboard sheets, and a ready-made Markdown document, as one JSON response. ### How much does it cost? One credit per video for /v1/scrape. New accounts get 100 free credits. One-time credit packs are $9 for 1,000 credits and $29 for 4,000 credits, and credits never expire. ### Do I need to manage proxies or cookies? No. VidCrawl handles YouTube access. You send a video URL and an API key. ### Can I get frames as well as text? Yes. /v1/frames returns full-resolution JPEGs at the timestamps you ask for, up to 20 per request and 1920px wide. ### Is the output deterministic? Yes. /v1/scrape runs no model, so the same video returns the same transcript every time. ## Related Pages - [YouTube transcript](https://vidcrawl.com/youtube-transcript) ([Markdown](https://vidcrawl.com/youtube-transcript.md)) - [TikTok transcript API](https://vidcrawl.com/tiktok-transcript-api) ([Markdown](https://vidcrawl.com/tiktok-transcript-api.md)) - [Video to Markdown](https://vidcrawl.com/video-to-markdown) ([Markdown](https://vidcrawl.com/video-to-markdown.md)) --- # TikTok transcript API > A TikTok transcript API that returns timestamped segments, post metadata, and a contact sheet of the clip in one POST, with the same response shape as YouTube. 100 free credits. Canonical URL: https://vidcrawl.com/tiktok-transcript-api Markdown URL: https://vidcrawl.com/tiktok-transcript-api.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp One POST returns what was said in a TikTok, with timestamps, the post's metadata, and a contact sheet of the clip. Same response shape as YouTube. ## What You Get ### Segments your code can use Each segment has a start and end in seconds, a formatted timestamp, and clean text. ### The post and its frames Author, caption, and duration, plus a contact sheet image covering the whole clip. ### One shape for every platform The fields match YouTube, Instagram Reels, and X, so you write the integration once. ## One request Authenticate with your API key and POST a video URL. One credit per video. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.tiktok.com/@neildegrassetyson/video/7482856405934918955"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### What does the TikTok transcript API return? Timestamped transcript segments, the full text, author, caption, duration, and a contact sheet of nine frames, as one JSON response with a Markdown version. ### What happens when a TikTok has no captions? VidCrawl transcribes the speech. The response says whether the text came from captions or from speech-to-text. ### How much does it cost? One credit per video for /v1/scrape. New accounts get 100 free credits. One-time credit packs are $9 for 1,000 credits and $29 for 4,000 credits, and credits never expire. ### Is the response the same as for YouTube? Yes. Every platform returns the same fields, so one parser handles YouTube, TikTok, Instagram Reels, and X. ## Related Pages - [TikTok transcript](https://vidcrawl.com/tiktok-transcript) ([Markdown](https://vidcrawl.com/tiktok-transcript.md)) - [YouTube transcript API](https://vidcrawl.com/youtube-transcript-api) ([Markdown](https://vidcrawl.com/youtube-transcript-api.md)) - [Video to Markdown](https://vidcrawl.com/video-to-markdown) ([Markdown](https://vidcrawl.com/video-to-markdown.md)) --- # Video to Markdown > Turn a YouTube or TikTok video into one clean Markdown file: front matter, chapters, timestamped transcript, and storyboard links. Copy it or download it. Free, no account. Canonical URL: https://vidcrawl.com/video-to-markdown Markdown URL: https://vidcrawl.com/video-to-markdown.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp Paste a video link and get one clean Markdown file: front matter, chapters, the timestamped transcript, and links to the storyboard. Ready for notes, RAG, or a prompt. ## What You Get ### Front matter Title, author, platform, duration, and transcript source as YAML, so your tools can index the file. ### Chapters and transcript The creator's chapters as headings and the transcript with a timestamp on every line. ### Small enough for a prompt An 18-minute video is about 26 KB of Markdown, far less than the video itself. ## Convert videos in code The Markdown is the `markdown` field of the /v1/scrape response. One credit per video. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.youtube.com/watch?v=1E3tv_3D95g"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### What is in the Markdown file? YAML front matter with the title, author, platform, and duration; the description and its links; chapters; storyboard links; and the transcript with a timestamp on every line. ### Can I use it in Obsidian or Notion? Yes. It is plain Markdown with standard front matter, so it works in Obsidian, Notion, and any other Markdown tool. ### Is it good for RAG and LLM prompts? Yes. The file is compact text with timestamps, so chunks stay traceable to the moment in the video they came from. ### Which videos can I convert? Public videos on YouTube (including Shorts), TikTok, Instagram Reels, and X. ### Is it free? Yes, in the browser, with a daily limit and no account. The API costs one credit per video, and new accounts get 100 free credits. ## Related Pages - [YouTube transcript](https://vidcrawl.com/youtube-transcript) ([Markdown](https://vidcrawl.com/youtube-transcript.md)) - [TikTok transcript](https://vidcrawl.com/tiktok-transcript) ([Markdown](https://vidcrawl.com/tiktok-transcript.md)) - [YouTube transcript API](https://vidcrawl.com/youtube-transcript-api) ([Markdown](https://vidcrawl.com/youtube-transcript-api.md)) --- # VidCrawl vs Supadata > A side-by-side comparison of VidCrawl and Supadata for video transcripts, storyboards, frames, and questions about a video, with pricing as published in November 2026. Canonical URL: https://vidcrawl.com/alternative/supadata Markdown URL: https://vidcrawl.com/alternative/supadata.md Agent Skill: https://vidcrawl.com/skill.md MCP Server: https://vidcrawl.com/mcp Both APIs turn video into text for AI. They differ in what comes back besides the words, and in how questions about a video are priced. Here is the comparison, including where Supadata is ahead. ## Side-by-Side Comparison | Feature | VidCrawl | Supadata | |---|---|---| | Transcript with timestamps | /v1/scrape (1 credit per video) | /v1/transcript (1 credit; AI transcript 2 credits per minute) | | Platforms | YouTube, TikTok, Instagram Reels, X | YouTube, TikTok, Instagram, X, Facebook | | Storyboard of the whole video | Included with every scrape | Not listed in the public docs | | Sharp frames at chosen timestamps | /v1/frames (1 credit per request, up to 20 frames) | Not listed in the public docs | | Questions about a video | /v1/agent (synchronous, 3 to 10 credits per question) | /v1/extract (asynchronous, 5 credits per minute, up to 55 minutes) | | Free tier | 100 credits on signup | 100 credits per month | | Paid plans | From $9 pack (credits never expire) | From $5 per month | | SDKs and MCP | Remote HTTP and stdio MCP server, /skill.md, OpenAPI 3.1, llms-full.txt | JavaScript and Python SDKs, MCP server | ## What You Get ### A storyboard with every transcript Each scrape includes small frames across the whole video, so a model can see where the detail is. ### Sharp frames on request Ask for exact timestamps and get full-resolution images, up to 1920px wide. ### Answers priced per question The agent endpoint is synchronous and costs the same for a short clip or a long talk. ## Try the same request Authenticate with your API key and POST a video URL. One credit per video. ```bash curl https://vidcrawl.com/v1/scrape \ -H "Authorization: Bearer $VIDCRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://www.youtube.com/watch?v=1E3tv_3D95g"}' ``` ### For AI Agents Prompt: `Read https://vidcrawl.com/skill.md and configure VidCrawl (MCP at https://vidcrawl.com/mcp or REST API) using my VIDCRAWL_API_KEY. Run a test scrape to verify.` - MCP server: https://vidcrawl.com/mcp - Agent skill: https://vidcrawl.com/skill.md - API reference: https://vidcrawl.com/api-reference.md ## Frequently Asked Questions ### When is Supadata the better choice? When you need Facebook video or an official JavaScript or Python SDK. Supadata has both; VidCrawl does not yet. ### When is VidCrawl the better choice? When your agent needs to see the video as well as read it: a storyboard of the whole video with every transcript, and sharp frames at the timestamps you choose. ### How do the two price a question about a video? VidCrawl charges 3, 5, or 10 credits per question by effort, whatever the video's length. Supadata's extract endpoint charges 5 credits per minute of video. ### Where do the Supadata facts come from? From Supadata's public pricing page, product pages, and changelog, read in November 2026. Check their site for current details. ## Related Pages - [YouTube transcript API](https://vidcrawl.com/youtube-transcript-api) ([Markdown](https://vidcrawl.com/youtube-transcript-api.md)) - [TikTok transcript API](https://vidcrawl.com/tiktok-transcript-api) ([Markdown](https://vidcrawl.com/tiktok-transcript-api.md)) - [Video to Markdown](https://vidcrawl.com/video-to-markdown) ([Markdown](https://vidcrawl.com/video-to-markdown.md))