Skip to content
ScribeCue
Transcript generator · YouTube, audio, video

Speech in, clean transcript out.

A YouTube link, a podcast episode, a Zoom recording or a voice memo — timestamps, speakers and four export formats.

No link handy?

Try:
FreeNo sign-upNot affiliated with YouTube
Two microphones whose sound waves become two colour-coded columns of text, one per speakerAUDIO · VIDEO → TEXT
A transcript generator turns recorded speech into written text with timestamps. ScribeCue does it from a YouTube link — free, unlimited, no sign-up — or from an audio or video file, which AI transcribes with speaker labels (120 minutes free a month). Rename speakers, then download TXT, Word, SRT or VTT.

Three sources, one transcript

SourceHowFreeSpeakers
YouTube videoPaste the link; we read its captionsUnlimitedNo
Audio file (podcast, interview, voice memo)Upload MP3, M4A, WAV, AAC, OGG or FLAC120 min a monthYes
Video file (Zoom, screen recording, your footage)Upload MP4, MOV, WebM or MKV120 min a month (shared)Yes

Need TikTok instead? Use TikTok transcript.

How to generate a transcript

  1. Pick your source. A YouTube link, or an audio or video file — a podcast episode, a voice memo, a Zoom recording.
  2. Generate the transcript. Links return in seconds from the captions; files are transcribed from the audio in about a minute per 30 minutes.
  3. Tidy it. Rename speakers and switch timestamps on or off.
  4. Export. TXT, DOCX, SRT or VTT — or copy it straight into your notes.

What a good transcript has — and what ScribeCue does about it

NeedWhat ScribeCue does
Readable, not a wall of fragmentsJoins caption lines and speech into sentences and paragraphs
Findable momentsTimestamps per paragraph or per line; click one to jump the video
Who said whatSpeaker labels on uploads, renamed once for the whole file
The format your tool wantsTXT, DOCX, SRT, VTT
The gist without reading it allAI summary with key points and chapters — 3 a day free
PrivacyUploads deleted after transcription; never used for training

Before and after: raw captions vs. ScribeCue

YouTube stores captions as short timed fragments, a few words each. Copied straight out of the Show transcript panel, that is what you get. ScribeCue joins the fragments into sentences and paragraphs, keeps one timestamp per paragraph and leaves every word as published. Three real examples, same seconds of each video:

VideoRaw caption linesScribeCue paragraph
Steve Jobs, Stanford commencement (15 min)0:47 Today I want to tell you three stories from my life. That's it. · 0:52 No big deal. Just three stories. · 0:55 The first story is about connecting the dots. · 1:01 I dropped out of Reed College after the first 6 months,[0:47] Today I want to tell you three stories from my life. That's it. No big deal. Just three stories. The first story is about connecting the dots. I dropped out of Reed College after the first 6 months…
Tim Urban, TED (14 min)0:19 Now, when a normal student writes a paper, · 0:21 they might spread the work out a little like this. · 0:23 So, you know -- · 0:25 (Laughter) · 0:26 you get started maybe a little slowly,[0:12] … Now, when a normal student writes a paper, they might spread the work out a little like this. So, you know -- (Laughter) you get started maybe a little slowly…
Ken Robinson, TED (20 min)0:43 There have been three themes running through the conference, · 0:46 which are relevant to what I want to talk about. · 0:49 One is the extraordinary evidence of human creativity[0:27] … There have been three themes running through the conference, which are relevant to what I want to talk about. One is the extraordinary evidence of human creativity…

Switch timestamps off and the same text copies as clean prose; switch them on, or download SRT, and every original line keeps its exact timing.

Transcript generator pricing, plainly

  • YouTube links: free and unlimited, no account, no ads.
  • Uploads: 120 minutes free every month, files up to 120 minutes.
  • More: Pro at $12/month (files up to 3 hours), or a one-off minute pack that does not renew. Details on Pricing.

Which file to download

You want to…DownloadTiming kept
Read, quote or paste into ChatGPT / NotionTXTOptional
Edit and share in Word or Google DocsDOCX (video title as the heading)Optional
Add subtitles in Premiere, Resolve, CapCut or re-upload to YouTubeSRTYes
Subtitles in a web player or HTML5 <track>VTTYes

Related guides

Frequently asked questions

Is there a free transcript generator with no sign-up?

Yes. ScribeCue generates YouTube transcripts free and unlimited without an account, and transcribes 120 minutes of your own audio or video free each month.

Can it transcribe a voice memo or a Zoom recording?

Yes. Upload the file — voice memos are usually M4A, Zoom recordings MP4 or M4A — and you get a timestamped transcript with speaker labels.

How long does it take?

A few seconds for a YouTube link; about a minute per 30 minutes of uploaded audio.

Which languages does it support?

Uploads: 30+ spoken languages, detected automatically. YouTube links: every caption track the video has, plus translation into 24 languages.

Can I rename the speakers?

Yes. On uploaded files, click a speaker name once to rename it everywhere; TXT, DOCX, SRT and VTT downloads all use the new names.

Is my recording kept?

No. Uploaded files are used only to make your transcript and are deleted automatically. They are never used to train models.

Which format should I download?

TXT or DOCX to read, quote or edit; SRT or VTT for subtitles, which keep the exact timing of every line.

More tools and guides