Skip to content
REMOTE MCP SERVER

YouTube Transcript MCP Server for Claude, ChatGPT & any MCP client

Connect once, then ask your AI to fetch YouTube transcripts with timestamps, transcribe recordings, find the exact passage, and export TXT, SRT, VTT or JSON.

  • 3 free YouTube caption pulls a month, no account
  • Re-reads of transcripts you already have are free
  • Plans from $3.99/month, plus a one-time credit pack
  • OAuth sign-in, no API key to copy

Ask about a video

Paste a YouTube link in the chat. Your client picks the right tool on its own. Example conversation:

You
Summarize this interview and quote what they say about pricing: https://www.youtube.com/watch?v=dQw4w9WgXcQ

transcriptlab_get_transcript · reading captions…

Illustrative example, not this video's actual captions
[0:42] We kept the first version simple on purpose.
[1:15] Pricing changed once we saw how people actually used it.
[2:03] The free tier stays free; heavy usage moves to a flat plan.

Assistant
They kept the first version simple, then changed pricing after watching real usage: “The free tier stays free; heavy usage moves to a flat plan” (2:03).

Connect in about two minutes

One URL, no local install: https://api.transcriptlab.dev/mcp. Connecting and listing tools needs no sign-in. The first tool call opens the TranscriptLab consent page, where you sign in or paste an API key.

Add a custom connector in Settings. Sign in on the first tool call.

https://api.transcriptlab.dev/mcp

Open Settings, then Connectors, choose Add custom connector, and paste the URL. The first tool call opens the TranscriptLab consent page.

Using a coding agent?Paste the instructions into your agent and it connects itself.

Prefer plain HTTPS from your own code? Start with the API quickstart for agents or the API reference.

What your AI can call

Fetching a transcript can use a credit on first delivery. Searching, re-reading and exporting transcripts you already have is free.

ToolWhat it doesCost
transcriptlab_get_transcriptGet the transcript of a YouTube video from its captions, optionally in another language.First delivery of a variant can use a credit
transcriptlab_retrieve_transcriptRead a YouTube transcript that is already published for your account, without starting a new fetch.Free for variants you already have
transcriptlab_discover_captionsList the caption languages and track types (manual or generated) a video offers.Free, subject to a monthly limit
transcriptlab_get_job_statusCheck whether a transcript job has finished.Free
transcriptlab_search_transcriptSearch, quote or page through a transcript you already have (keyword, regex or sequential chunks).Free
transcriptlab_list_transcriptsList the transcripts in your library, newest first.Free
transcriptlab_transcribe_fileTranscribe an audio or video file attached to the conversation with speech-to-text.Credits per audio minute
transcriptlab_transcribe_media_urlTranscribe a public https link to an audio or video file.Credits per audio minute
transcriptlab_get_speech_transcriptRead the speech-to-text result for a file or media link you submitted.Free
transcriptlab_export_linkCreate a 10-minute download link (TXT, SRT, VTT, Markdown or JSON) for a transcript you have.Free; needs a signed-in connection
transcriptlab_get_usageShow your plan, remaining credits and usage this period.Free
transcriptlab_openOpen the interactive TranscriptLab view: paste a link, upload a file, browse your library.Free
transcriptlab_open_audioEntry point a host uses when you open an audio or video file with the connector. You do not call it yourself.Credits per audio minute

Things to ask

  • Get the transcript of https://www.youtube.com/watch?v=dQw4w9WgXcQ and summarize it.
  • Which caption languages does that video have?
  • Find where they mention pricing in that transcript.
  • Transcribe this attached interview recording and label the speakers.
  • Transcribe https://example.com/interview.mp3.
  • Give me that transcript as an SRT file.
  • Show my earlier transcripts, and how many credits do I have left?

Start free, upgrade when you need to

Guests pull 3 YouTube captions a month without an account. Credits are charged when a transcript is delivered, and re-reading a transcript you already have is free.

Free account

$0

10 one-time credits

  • 1 credit per YouTube transcript
  • 1 credit per audio minute of speech-to-text
  • Transcript library, search and exports

Starter

$3.99

per month · 1,000 credits

  • Batch and channel jobs up to 250 videos
  • 60 requests/min · 500 discoveries/mo
  • Full API access with your own keys

Credit pack

$4.99

one-time · 1,000 credits

  • No subscription required
  • Stacks on any plan allowance
  • Credits never expire monthly

Agents can also pay per transcript with x402: $0.01 USDC on Base, no API key. See full plan details or compare with Supadata.

Frequently asked questions

Do I need an API key to connect?

No. The server uses OAuth 2.0 with dynamic client registration, so Claude and other MCP clients connect with just the URL. Connecting and listing tools needs no sign-in; the first tool call opens a TranscriptLab consent page where you sign in or paste an API key. Clients that cannot run a browser flow can use a TranscriptLab API key instead.

What counts as a credit?

Fetching a YouTube transcript uses 1 credit the first time you request that variant. Reopening, searching and exporting a transcript you already have is free. Speech-to-text is metered per audio minute: 1 credit per minute on the standard model, 10 on the premium model that labels speakers. A free account includes 10 one-time credits.

What happens if a video has no captions?

The server returns an explicit no-captions result. It never transcribes automatically. You can opt into speech-to-text with an attached file or a public https media link, metered per audio minute.

Which clients work with it?

Claude (claude.ai, Claude Code, Cowork), ChatGPT, Cursor, Codex, and any MCP client that supports remote streamable HTTP servers. The server registers itself through dynamic client registration, so no client ID is needed.

What gets sent and stored?

The server receives the YouTube links, files and media URLs you ask your client to process. Delivered transcripts stay in your TranscriptLab library until you delete them; you can delete individual transcripts or your whole account. See the privacy policy at transcriptlab.dev/privacy.

Can I use it from my own code?

Yes. The same account works over plain HTTPS with an API key: POST /v1/transcripts for YouTube reads, POST /v1/media for media files, plus batch and channel jobs. Agent setup notes are at transcriptlab.dev/api.md and the full reference at transcriptlab.dev/docs.

FOR AGENTS

Machine-readable setup

Two plain-markdown documents written for coding agents: connection instructions with every tool parameter, and an API quickstart with cURL, Python and JavaScript examples.

Keep reading: the full MCP reference, the API docs, API comparisons, free YouTube tools, or support (hello@transcriptlab.dev).

Connect once.
Read any video.

Add the server to your AI client, sign in on the first tool call, and start with a YouTube link.

Connect your AI