Your own channel's back catalogue
Creators
Turn published videos into scripts, blog posts and descriptions without re-typing what you already said on camera.
YouTube transcript generator: paste a link, get the text.
Drop your video or audio hereor
MP4, MOV, MP3, WAV, M4A. Up to 2 GB.EnglishFollows source
Paste a public YouTube link and Subanana fetches the audio for you — nothing to download, no browser extension to install. You get a transcript with speakers separated, punctuation and paragraphs restored, and every line timecoded. Shorts work too, and so do public Instagram links. 95+ languages. Subanana averages 98% accuracy. Preview the first 15 minutes of any video free.
No card needed. Preview the first 15 minutes free.
How it works
Pasted link
youtube.com/watch?v=… · public video
Public YouTube and Instagram links — no downloadShorts come in the same way as long videos
Transcribe
00:12
Today we're setting up a home studio.
00:27
First, the question everyone asks: light.
00:41
All the gear is linked in the description.
SpeakersSpeaker 1Punctuation restored
Text formats
TXTDOCXXLSXMarkdownTranscript
TXT · DOCX · XLSX · Markdown
Subtitle file
SRT · VTT
Translated text
one of 95+ languages
Summary
14 built-in templates
Ask the video
answers cite the line
Nine reasons to stop pausing and rewinding YouTube videos.
From the pasted link, through recognition and proofreading, to the text file you actually need — all of it in one place.
Paste the link — the video never touches your disk
- Public YouTube linksLong videos and Shorts alike; Subanana fetches the audio itself.
- Instagram tooPublic posts and Reels come in the same way.
- Or upload the filePrivate or restricted video? MP4, MOV, MP3, M4A and more drag straight in.
- Long videos stay wholeUp to 8 hours and 30 GB per file, on every plan.
It knows the language the video is in
- 95+ languagesPick the spoken language and the system routes to the model that benchmarks best for it.
- Not a copy of the auto-captionsThe speech is transcribed from the audio, so videos without captions work too.
- Speakers kept apartEach voice gets its own label, and punctuation and paragraphs come back.
- Translate while you are hereThe same transcript can also come back in one other language.
Whatever text file you need, it exports
- Text and tablesTXT, DOCX, XLSX and Markdown — speakers and timestamps included.
- Subtitle filesSRT and VTT, single-language or bilingual.
- Every track at onceAll tracks in one ZIP, in the format you pick.
- Transcript and subtitles, one jobThe document and the SRT or VTT come from the same project.
Proofread it before anyone reads it
- A score out of 100Suggestions grouped by kind, usually back in ten to thirty seconds.
- Approve group by groupOnly the groups you accept get applied; the rest stay untouched.
- Timecodes do not moveProofreading changes wording, never the timing.
- Entirely skippableNothing changes until you press the button.
Invented sentences do not reach your transcript
- Two layers of detectionAI hallucination detection plus an engine-side check runs over every segment; suspect lines get flagged.
- Automatic re-run on another engineFlagged segments go to a different engine instead of being written through.
- Silence stays silenceA pause is a pause, not a sentence the model imagined.
The same transcript gives you more than a transcript
- Summaries and highlights14 built-in templates pull the points out of a long video, or write your own.
- Show notes and quotesThe Show Notes template lays out a long video's topics; quotable lines are easy to pull.
- Descriptions and notesVideo descriptions and bullet lists come from the same text.
- Ask the videoAsk the AI assistant directly — every answer is grounded in the transcript.
Names and jargon come out spelled right
- Workspace glossarySave people, products and in-house terms once; every later file uses your spelling.
- Per project or everywhereMark a term universal, or attach it to a single project.
- Import what you already haveLoad a CSV or XLSX, or let the AI pull candidates from a PDF.
- Review before it appliesSee exactly which terms were aligned, before anything changes.
Need subtitles too? Style them here
- Two style basesOutline with a shadow, or a background block with adjustable opacity.
- Adaptive sizingLong lines reflow instead of running off the frame.
- Two tracks, styled apartSource and translation never fight for the same line.
- Preview as you goFont, size, colour, alignment and padding, on the real frame.
Want the finished video, not just the text?
- Up to 4K720P, 1080P, 2K or 4K, rendered exactly as previewed.
- Bilingual burn-inBoth languages on screen, each with its own styling.
- Your watermark, or noneHide the default watermark entirely, or swap in your own.
- Renders in the backgroundKeep editing while it runs; the export is the version you pressed on.
You found the video. Now you need what was said in it.
Four kinds of viewer, one problem — watching a 40-minute video again to find one sentence.
Lectures and talks shared on YouTube
Students and researchers
Search a recorded lecture for the one passage you need, and quote it with the minute it was said.
Interviews and press conferences
Journalists and writers
Pull exact, attributable quotes from a public video without transcribing it word by word.
Competitor and industry channels
Marketers and analysts
Keep what a dozen videos said as searchable text, instead of spending a day watching them.
Everything else.
None of these is why you would switch, but every one of them is there when you have to hand something over.
File uploadPaste a linkBrowser recordingScreen recordingSpeaker detectionCustom glossaryFind and replaceWaveform timelineAI proofreadAI summariesAsk the videoSRT · VTT exportDOCX · XLSX exportTXT · Markdown exportAll tracks as one ZIPShare links without sign-inWorkspace roles
The details live in the product — a free workspace takes about a minute.
See it in the productBefore you startthe questions everyone asks
Four steps. (1) Copy the video's public YouTube URL and paste it into Subanana. (2) Pick the language spoken in the video. (3) The AI fetches the audio, transcribes it, separates the speakers and restores punctuation and paragraphs. (4) Review the transcript in the editor and export it. There is nothing to download and no browser extension to install. The first 15 minutes of every video are free to preview.
Yes. Subanana does not copy the captions YouTube already shows — it listens to the video's audio and transcribes the speech itself. So it works on videos with no captions at all, and on videos whose auto-captions are poor.
Yes. Public Shorts work the same way as ordinary videos, and public Instagram links are fetched the same way too.
Link import covers public videos. Private, members-only and restricted videos cannot be fetched, and a live stream can only be imported once it has ended. If you have the file, upload it instead — MP4, MOV, WEBM, MP3, M4A, WAV and other common formats drag straight into the browser.
A free account previews the first 15 minutes of each video's transcript, 3 files a month, no credit card. Downloading or copying the transcript, or downloading a subtitle file, is a paid feature — so you can check how well your video transcribes before paying anything.
Up to 8 hours and 30 GB per file, on every plan. A long lecture or a full podcast episode goes in whole, without splitting.
Subanana averages 98% accuracy. Results move with how clearly people speak, background music and noise, and how much jargon is involved. Adding channel names and technical terms to the glossary noticeably improves how proper nouns come out.
Transcripts export as TXT, DOCX, XLSX or Markdown with speakers and timestamps, and subtitles as SRT or VTT — or every track at once as a ZIP, in the format you pick. PDF export is not available. A transcript can also come back translated into one other language, chosen from 95+.