Podcast transcript example

Sample coming soon

What is a YouTube podcast transcript

A YouTube podcast transcript is the full text of an episode that is on YouTube, with a label on each speaker and a timestamp on each paragraph. It is what you search, quote and paste into show notes.

One episode, four outputs

The transcript with a name on every speaker turn. The summary in paragraphs. Three lines with their timestamp, ready for the episode page or a post. The SRT from a Subtitles (SRT or VTT) job on the same episode, for the clip editor. Each one is a real output of the sample above.

We picked the three lines by hand. The tool gives you the transcript; you choose the lines.

Chapters for the description

Once you own the job, ask the built-in AI for a timestamped list of sections and paste it into the description as 0:00 Title. It reads the first 24,000 characters, about 25 to 35 minutes of speech.

Export TXT and DOCX, share a read-only page

Export the transcript as TXT or DOCX with speaker names and timestamps on or off. Share a read-only link to the text.

Automate it

API and MCP are included on every plan. Your 10 free minutes work through the API too. Each call takes one YouTube URL and returns one transcript, so a weekly show is one call a week.

YouTube auto captions vs YoutubeToText for an episode

YouTube auto captions vs YoutubeToText for an episode
FeatureYouTube auto captionsYoutubeToText
Speaker namesDashesLabels you can rename, free
ParagraphsNoOn every speaker change, at most every 30 seconds
TimestampsEvery few secondsOne per paragraph, toggle on or off
Filler wordsKeptCleaned by default, verbatim on request
SummaryNoParagraphs in the episode's language
ExportsNone for videos you do not ownTXT and DOCX; SRT and VTT from a Subtitles (SRT or VTT) job
Episodes over 1 hourAuto captions may not existUp to 12 hours

How it works

  1. 1

    Rename Speaker 1 and Speaker 2 to the hosts

    Click a speaker chip and type the name. Rename once, applied everywhere.

  2. 2

    Open Summary, then copy lines from Transcript

    Read the summary for the show notes draft. Back in Transcript, copy the lines you want with their timestamp.

  3. 3

    Export, run Subtitles for clips, share

    Export .txt or .docx for the episode page. Run a Subtitles (SRT or VTT) job on the same link for SRT and VTT. Share the read-only text page with your editor.

Things worth knowing

Minute 47 of a 90-minute episode

A long episode is not one request. Videos over 10 minutes are split into chunks, each chunk is transcribed on its own, and the parts are merged back into one transcript. You get one transcript, not several. Speaker labels are tracked across the whole episode, so the host is the same speaker at minute 47 as at minute 2. The ceiling is 12 hours per video, which covers a full-day live show. The sample above is a full real episode, run once on our own account, and its length is stated next to the player. Play it from the middle and watch the active word follow the audio. If you need to check a line, click any word to jump the player to that second.

Show notes and chapters

The summary is a set of paragraphs in the language of the episode. It has no bullet list and no timestamps, so it is a first draft of the show notes, not the finished post. Take the timestamped lines from the transcript yourself: open Transcript, find the moment, copy the paragraph with its timestamp. For chapters, YoutubeToText has no chapter output. Once you own the job, open Ask AI and ask for a list of the sections with a timestamp and a title, then reformat the answer as 0:00 Title in the YouTube description. Ask AI reads the first 24,000 characters of the transcript, about 25 to 35 minutes of speech, and answers in at most 700 tokens, so on a long episode ask it about the part you need.

A video podcast that is also on Spotify

YoutubeToText takes a YouTube link only. If your show is on Spotify, Apple Podcasts and YouTube, paste the YouTube upload. The video must be public or unlisted; a private video cannot be read. The transcript is the same whichever platform you publish the text on, so one job covers the episode page, the newsletter and the social posts. If the guest was recorded in a second language, run Translate on the job afterwards; the translation keeps the speaker labels and paragraphs. When you publish the full transcript on your site, credit the show, the episode, the host and link back to the episode, the same way you would quote any other source.

The problem in their words

I still check for a transcript, and if there is none I move along. You can't search audio. You can't skim audio. You can't easily hyperlink to audio, copy-and-paste audio, or auto-summarize audio.
Hacker News
Right now I'm doing this manually by copy/pasting into ChatGPT but I want to automate this aspect.
Hacker News

What a typical 90-minute episode costs

Free

10 min

Your first 10 minutes are free. They cover the start of a 90-minute episode; the rest is locked until you unlock it.

Just this video

...

One payment for a 90-minute episode, 90 minutes. No subscription.

Creator

... / month

600 minutes every month, the smallest plan that covers a 90-minute episode.

The Deep Dive

...

600 minutes, one payment, credits never expire.

See all plans

FAQ

Questions.
Answered.

Can't find what you're looking for?
Contact us.

Yes. Speaker detection is on for every job, so each turn gets its own label and one of six colours. The labels start as Speaker 1 and Speaker 2. Click a chip in the editor, type the host's name, and the name applies to every turn, the Translate tab and every export. A guest who joins at minute 30 gets a new label when they first speak.
Yes, in two places. In the editor, the Timestamps toggle hides them on screen and the Speakers toggle hides the names. In the export menu, the checkboxes Include speaker names and Include timestamps set what goes into the TXT, DOCX and Copy output. Switch both off and you get plain paragraphs to paste into your blog editor.
Partly. The summary is a set of paragraphs in the spoken language of the episode, with no lists and no timestamps. Copy it as the draft, then add the timestamped lines you pick from the transcript and the links your guest mentioned. The transcript is the full text; show notes are the short version you write from it.
Not as a separate output. Once you own the job, open Ask AI and ask: List the sections of this episode with a timestamp and a title. Reformat the answer by hand as 0:00 Title, one per line, following YouTube's chapter rules. Ask AI reads the first 24,000 characters of the transcript, about 25 to 35 minutes of speech, and allows 40 questions per hour.
Only when the episode is also on YouTube. Paste the link of the YouTube upload; a Spotify or Apple Podcasts link will not work. The video must be public or unlisted. Private videos cannot be read, so set the upload to unlisted first if you do not want it public yet, run the job, and switch it back afterwards.

Updated September 2026

Ready when you are

Paste your episode link

Get the transcriptFirst 10 minutes free. No credit card required.