Subtitle Generator

Generate timestamped subtitles from your video

Upload a video or paste a YouTube link and get a WebVTT caption file back — every line with a start and end time, ready to drop into a player, a caption editor, or a subtitle track.

WebVTT (.vtt) outputMillisecond cue timingsEditable before downloadUp to 60 minutes
Used by 170,000+ students worldwide

Quick answer

How do I generate subtitles for a video?

Open Transcribe on the Scholarly home screen, add your video file or a YouTube URL, and choose Timestamped captions (.vtt) as the output format. Scholarly transcribes the spoken audio and writes a WebVTT file with a timed cue for every line. It runs in the background and saves to your library, where you can edit it and download it.

  • Standards-compatible WebVTT. The file opens with a WEBVTT header and numbered cues in HH:MM:SS.mmm format — the caption format browsers and HTML5 video read natively.
  • One credit per video. A single AI credit covers the whole video regardless of length, and is returned automatically if the job fails.
  • Editable before you ship it. The .vtt lands in your library as a text file. Fix a name, a term, or a line break in the editor, then download it.

You get a caption file, not a burned-in video. That is the point — one .vtt works across your player, your LMS, and your editing tool without re-rendering anything.

Updated August 2026

Add the video

Upload an MP4, MOV, WebM, or other supported file — or paste a YouTube URL.

Choose timestamped captions

Pick the .vtt output format instead of plain text. Every line comes back with a start and end time.

Edit and download

The finished .vtt opens in your library. Correct anything that needs it, then download the caption file.

Where a .vtt file earns its keep

Captions on a course video

Attach the track to a lecture or training video so people can follow along, search it, or watch with the sound off.

Accessibility requirements

A timed caption track is the baseline accommodation for recorded material — and the starting point for a reviewed, corrected version.

Clip-finding in long footage

Cue times tell you exactly where a sentence lives, so pulling a 40-second clip out of an hour is a lookup, not a hunt.

A base for translated subtitles

Get the source-language timings right first; a translator can then replace the text without redoing the timing work.

Subtitle generator

A timed WebVTT caption file for one video, which you download and use wherever you need it.

Plain-text transcript

The same words with no timings — better for reading, searching, quoting, and feeding to an AI chat.

Built-in player captions

YouTube and most platforms auto-caption on their own, but the track stays locked to that platform. A .vtt file is yours.

What the file actually looks like

A WebVTT file is plain text. It starts with the WEBVTT header, then a numbered cue for each line, then a timing row in the form 00:01:24.500 --> 00:01:29.120, then the spoken text. Because it is text, you can open it anywhere — Scholarly's own editor, a caption tool, or a code editor — and because the timings are written in milliseconds, cues land where the words were actually spoken rather than snapping to whole seconds.

Correct it before you publish it

Auto-generated captions are a first draft, not a finished one. Names, acronyms, and technical vocabulary are where speech-to-text most often slips, and those are exactly the words a viewer notices. The .vtt is saved as an ordinary library file, so open it, scan for proper nouns and jargon, fix them, and download the corrected version. That review pass is a few minutes and it is the difference between captions that help and captions that distract.

Honest limits

The output is WebVTT only — there is no .srt export, and captions are never burned into the video itself. There are no speaker labels: the cues carry what was said, not who said it, so a two-person interview reads as one continuous track. There is no translation step, so the subtitles come back in the language that was spoken. Videos are capped at 60 minutes each, checked before you are charged. And caption quality follows audio quality — a distant microphone, overlapping speakers, or loud background noise all show up in the text.

Keep exploring

Related tools

Other ways to get text out of a recording.

Video to text

The same transcription as a plain-text file for reading and search.

Audio to text

Voice memos, interviews, and recordings converted to a transcript.

YouTube transcript

Pull the full transcript of a YouTube video from its URL.

Lecture transcription

A full class captured as searchable, timestamped text.

AI lecture recorder

Record a session live and get notes alongside the transcript.

Text-to-Speech

The trip in reverse — turn a document into one MP3.

Frequently Asked Questions

What subtitle format do I get?

WebVTT (.vtt) — the caption format browsers and HTML5 video support natively, and the one most modern players, editors, and learning platforms accept. The file is standards-compatible, with a WEBVTT header and millisecond cue timings.

Can I get .srt files?

Not directly. Scholarly exports WebVTT only. The two formats are close relatives, so if a specific tool requires .srt, a free converter will turn the .vtt into one in a step.

Are the subtitles burned into the video?

No. You get a separate caption file, which is usually what you want — one track works across players and platforms, and you can correct it later without re-rendering the video.

Do the subtitles identify who is speaking?

No. The cues carry the spoken text without speaker labels. For material where who-said-what matters, record through AI Meeting Notes, which keeps speaker turns.

Can I generate subtitles for a YouTube video?

Yes — paste the URL instead of uploading a file. Scholarly uses the video's own transcript for the text and writes it out as a .vtt you can download and keep.

How long can the video be?

Up to 60 minutes per job. The length is checked before any credit is charged, so an over-length video is rejected rather than partially captioned.

Can I fix mistakes in the captions?

Yes. The .vtt is saved as a normal text file in your library — open it in the editor, correct names and technical terms, and download the corrected version.

Get a caption file for your next video

One credit per video. Editable WebVTT, downloaded and yours.

Free

See what it does with one of your own sources.

$0

/month

Free forever

No card required.

  • 3 lifetime AI Chat messages

  • 1 free AI creation total

  • 2-minute podcasts and video lectures

  • 1 free file upload total (8MB)

  • 5 lifetime quiz questions

  • 1 completed practice exam total

  • 15 lifetime voice minutes

  • 32-page PDF to flashcards

  • 500 lifetime autocomplete words

Use it to generate flashcards, improve a deck, or create a podcast, video lecture, slides, infographic, mind map, study guide, worksheet, spreadsheet, story book, timeline, SOP, flowchart, lesson plan, or outline — or run Deep Research or turn a recording into AI Meeting Notes.

Premium

Most Popular

Steady weekly output from the material you already have.

$12

/month

Billed yearly at $144 · save $216

  • Everything in Free, plus:

  • 10 AI creations per week

  • Unlimited AI chat & autocomplete

  • Podcasts up to 60 minutes, videos up to 45 minutes

  • Unlimited file uploads (up to 300MB)

  • Unlimited study sessions

  • Unlimited exams & quizzes

  • 1000-page PDF to flashcards

  • Export to Anki

  • Priority support

Laureate

For work where being right matters more than the price.

$99

/month

billed monthly · cancel anytime

For frontier models & 8x more AI Creations

Our most advanced and most expensive tier.

  • Everything in Premium, plus:

  • 80 flexible AI creation credits every week

  • 80 AI creations per week

  • Podcasts up to 60 minutes, videos up to 45 minutes

  • Unlimited uploads up to 1 GB, plus 3,000-page PDFs

  • 12 hours of voice mode per day

  • Priority support and early access to new Frontier models

Pricing shown in USD. Local currency may be available for Premium in app.

Compare plans

AI chat

Premium and Laureate include unlimited AI chat. GPT 5.6 Sol and Claude Opus 5 are reserved for credit-metered AI creations.

Free
3 total
Premium
Unlimited
Laureate
Unlimited

AI creations

AI creations share one credit balance across every creation tool. Standard models use 1 credit; Frontier models Sol and Opus use 3.

Free
1 total
Premium
10/week
Laureate
80/week

Podcast length

Free episodes are fixed at 2 minutes. Paid plans can set a target length up to 60 minutes.

Free
2 minutes
Premium
Up to 60 minutes
Laureate
Up to 60 minutes

Video lecture length

Free lectures with a length control are fixed at 2 minutes. Paid plans can set a target up to 45 minutes. Short uses its own short video format.

Free
2 minutes
Premium
Up to 45 minutes
Laureate
Up to 45 minutes

File uploads

Free
1 total (8MB)
Premium
Unlimited (300MB)
Laureate
Unlimited (1 GB each)

PDF to flashcards

Free
32 pages
Premium
1000 pages
Laureate
3000 pages

Practice questions

Free
5 total
Premium
Unlimited
Laureate
Unlimited

Practice exams

Free
1 total
Premium
Unlimited
Laureate
Unlimited

Voice mode

Free
15 min total
Premium
2 hr/day
Laureate
12 hr/day

Autocomplete

Free
500 words total
Premium
Unlimited
Laureate
Unlimited

Export to Anki

Free
—
Premium
Included
Laureate
Included

Support

Free
Standard
Premium
Priority
Laureate
Priority

What customers say

Scholarly has enhanced the quality of notes and questions I administer to my tutees. Insightful, to the point.

TD Georgas

TD Georgas

Tutor

I have very good experience with Scholarly it summarize me scientific text in hovel academic level with citation. I use this for any therapeutic area . It is great and useful tool.

Diana

Diana

Scholarly user

Scholarly has been a valuable tool for my studies. The AI-generated flashcards and intuitive features make organizing and retaining information much easier.

Briana

Briana

Scholarly user

This app is great for studying for big test. Drop your PDF's in the system and it'll do the trick. You can organize it specifically for your needs.

Kelvin

Kelvin

Scholarly user

Your questions, answered

Is Scholarly free to use?

Yes! The free plan includes core study tools with lifetime allowances: 3 AI Chat messages, 500 autocomplete words, 5 quiz questions, 15 voice minutes, 1 practice exam, one free AI creation total, and 1 file upload. These allowances do not reset. Upgrade to Premium for 10 AI creations per week and unlimited uploads.

What uses my free AI creations?

Generating flashcards, improving a flashcard deck, making a podcast, creating a video lecture or infographic, building slides, a spreadsheet, or a story book, making a mind map, study guide, or worksheet, having an AI Agent create a timeline, SOP, flowchart, lesson plan, or outline, running Deep Research, or processing a recording uses your free AI creation. It is a lifetime free credit and does not reset. AI Chat, autocomplete, quiz practice, voice, exams, and file uploads have separate lifetime allowances.

Can I cancel anytime?

Absolutely. There are no contracts or commitments. You can cancel your subscription at any time from your account settings, and you'll keep access until the end of your billing period.

What payment methods do you accept?

We accept all major credit and debit cards through Stripe. Pricing is displayed in USD by default, but local currency is available in the app.

Can I use Scholarly with a class or school?

Yes. For a school or organization-wide rollout, contact us at hello@scholarly.so and we'll help you find the right setup.

What happens when I hit a free plan limit?

You'll see a prompt to upgrade. Your existing work is never lost — limits only apply to new actions. Free-plan allowances are lifetime credits and do not reset. Premium includes 10 AI creations per week, podcasts up to 60 minutes, video lectures up to 45 minutes, unlimited uploads, chat, autocomplete, quizzes, and exams, plus more daily voice time.