Whatever your agent stack — raw HTTP, MCP, or agent skills — the same engine feeds it clean, cited, timestamped YouTube text.
See the integration docs
curl "https://bulktranscripts.co/api/v1/transcript?video=VIDEO_ID" \
-H "Authorization: Bearer YOUR_API_KEY"claude mcp add --transport http bulktranscripts https://bulktranscripts.co/mcpcurl -fsSL https://bulktranscripts.co/skill.md \
-o ~/.claude/skills/youtube-transcripts/SKILL.mdThree ways, all backed by the same engine: the BulkTranscripts REST API (any language, a free API key as Bearer token), the hosted MCP server (Claude, ChatGPT, Cursor, VS Code, Codex), or the agent skill file for coding agents. Each returns clean transcript JSON, supports search and channel listing, and offers free new-upload polling for monitoring.
Everything below runs on the same engine as the web app.
A REST API for code and no-code tools (n8n, Make, Zapier call it with one HTTP node). An MCP server for Claude, ChatGPT, Cursor, and friends. And an agent skill — a single SKILL.md your coding agent installs once and then knows the whole API. All three share credits, cache, and the same underlying extraction chain; per-client setup lives in the integration guides.
Transcript responses carry everything a retrieval pipeline wants: stable video ids, titles, channels, upload dates, language and caption source, full text, silence-grouped paragraphs (natural chunk boundaries), and per-segment timestamps for deep-linking back to the exact moment in the video.
Agent workloads re-read the same sources constantly. Here, every extraction lands in a shared cache, so reads return in milliseconds without another network fetch. The first addition to an account's library costs one credit; its second, tenth, and thousandth reads are free. Daily research re-runs only pay for new library items.
The latest-uploads endpoint is free. The intended loop: poll it on a schedule, diff the video ids against what you have, extract only the new videos, hand transcripts to your summarizer. A daily channel brief costs a credit only on days the creator actually posts.
Authentication is one string in a header: create a free API key once at /app → MCP & API → API keys, or use the license key a credit pack issues. Give your agent the key as an environment variable and it meters itself with the billing block every response includes — and tops up at the purchase_url a 402 hands it, without the key ever changing.
It is plain HTTP GET with JSON responses and an OpenAPI spec at /openapi.json — one requests.get() call, or point a codegen tool at the spec.
Use the generic HTTP request node: GET https://bulktranscripts.co/api/v1/transcript?video={{url}} with an Authorization header. The free latest-uploads endpoint makes a clean trigger.
Start from the paragraphs array — paragraphs are grouped by natural silence gaps, which beats fixed-size chunking for spoken content. Keep the segment timestamps alongside to cite moments.
Yes — list the channel (up to 1,000 videos), then fetch transcripts; the web app's bulk mode and the API share the same cache, so nothing is ever extracted twice.
Sign in with Google, create a key, make the first call. No card.
Stuck on setup? Email hello@bulktranscripts.co with the app or code you are using and what you see. A person answers, usually within a day.
Updated