GeezerVison

The World Wide Web, restored to 800 pixels of glory.

GeezerVison is showing transcriptfetch.com — The transcript API for social media video | TranscriptFetch

Transcript API for developers

Social media video, as structured data.

Send a YouTube, TikTok or Instagram link. Get back timestamped text as JSON, from published captions or from the audio when there are none.

Get a free API key Read the docs

50 free credits
No card required
Failed fetches are never billed

curl -X POST \
  https://transcriptfetch.com/api/v2/transcripts/video \
  -H "Authorization: Bearer tf_live_••••" \
  -d '{"video": "https://youtu.be/bNpx7gpSqbY"}'

{
  "ok": true,
  "data": {
    "kind": "transcript",
    "platform": "youtube",
    "video_id": "bNpx7gpSqbY",
    "duration": 401,
    "source": "captions",
    "segments": [
      { "start": 41.0, "text": "I studied hundreds of companies" },
      { "start": 46.2, "text": "Five factors shaped their outcomes" },
      { "start": 52.3, "text": "One factor stood above the rest" },
      … 43 more
    ]
  }

1,700,000+Successful transcripts fetched

0.9sTypical response, last 7 days

99.9%API uptime, independently monitored

500+Developers served

Who it's for

Built for developers.

Plain REST, real SDKs and one predictable JSON shape. Whether it is a feature in your app or a job in your pipeline.

In your app

Add transcripts to a product feature without maintaining a scraper.

SDKs for Node and Python, or plain REST
One key in an env var, no proxies or headless browsers
50 free credits while you build

One video, from an API route

const t = await tf.transcripts.video(url);
return Response.json(t.segments);

In your pipeline

Feed whole channels into search, a model or a data warehouse.

One schema across YouTube, TikTok, Instagram and files
Batch up to 50 videos, page through channels and playlists
Monitors pick up new uploads on a schedule

Pull a whole channel

await tf.transcripts.channel("@3blue1brown", { limit: 50 });
await tf.transcripts.batch(videoIds); // up to 50

What people build

Real products, a few calls each.

Six products you can build on transcripts, and the calls behind each one.

Podcast search

Index every episode of a show and let listeners search by what was actually said. Each result jumps to the second it was spoken.

channelbatchsegments

Video summarizers

Paste a link, get chapters and notes back in seconds. One call returns the full timed transcript to feed your model.

videosegments

Course Q&A bots

Load a whole lecture playlist, then answer student questions with a link to the exact moment in the video.

playlistsegments

Slack link bots

Drop a TikTok, Reel or YouTube link in a channel and the bot replies with what the video says.

videosegments

Trend tracking

Search a topic every week and read what creators across TikTok and YouTube are saying about it.

searchbatch

New-episode digests

Watch the channels you follow and email a summary of every new upload, without polling them yourself.

monitorschannel

How we compare

Benchmarked against the alternatives.

Same URLs, sent to both APIs at the same instant, one attempt each. We count how many transcripts come back and how long the full text takes to arrive.

We built and ran these benchmarks. The script, every URL and every raw measurement are public, so you can run it with your own keys.

vs a leading multi-platform transcript API

28 Sep 2026 · 360 URLs · their paid Pro plan

Platform	Transcripts returned	Median time to full text
YouTube	120 / 120	1.1 s 5.4 s
TikTok	118 / 108	1.3 s 18.4 s
Instagram	118 / 96	5.9 s 19.9 s

TranscriptFetchThemMedian over URLs both returned

vs a popular YouTube transcript API

29 Sep 2026 · 500 YouTube URLs · their paid plan

Platform	Transcripts returned	90th percentile time
YouTube	500 / 463	1.1 s 3.0 s

TranscriptFetchThemp90 over URLs both returned

Coverage

Three platforms.
One transcript API.

Platforms3

Also on every key

YouTube API

Transcripts, search, channels, Shorts, playlists and monitors

YouTube Transcript API

TranscriptPOST/api/v2/transcripts/video
SearchPOST/api/v2/transcripts/search
Channel VideosPOST/api/v2/transcripts/channel
PlaylistPOST/api/v2/transcripts/playlist
ShortsPOST/api/v2/transcripts/channel
Channel MonitorPOST/api/v2/monitors

One Bearer key and one JSON envelope on every platform.Read the docs

Transcript APIs

MCP servers

FAQ

Before you write the first line.

A successful caption fetch or listing costs 1 credit. AI Fallback Transcription costs 1 credit per started 5 minutes of audio, billed only when the transcript is delivered. Failures are free.

We transcribe the audio instead. The response has the same shape, with source set to "audio". Long files run as a job you can poll for free.

Yes. npm install transcriptfetch for Node and pip install transcriptfetch-sdk for Python. Or call the REST API with any HTTP client.

Keep your key server-side. Put the call in an API route or server function and send the result to your frontend.

Every response includes usage.balance. You can also call tf.me(), which validates the key and reads the balance for free.

Get started

Your first transcript is one request away.

50 free credits
No card required
Failed fetches are never billed

Start fetching Read the docs

YouTube0:42No framework, just the standard library and one router.
TikTok0:12Okay so nobody talks about this part of moving cities.
Instagram0:27Toss the noodles straight from the pot.
YouTube12:04We charged from day one.
Instagram0:18Most houseplants die from too much water, not too little.
YouTube0:42No framework, just the standard library and one router.
TikTok0:12Okay so nobody talks about this part of moving cities.
Instagram0:27Toss the noodles straight from the pot.
YouTube12:04We charged from day one.
Instagram0:18Most houseplants die from too much water, not too little.

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.