Paste an existing transcript

Video tutorial

You can read all the instructions step by step in this page, but if you feel like watching the video tutorial instead, here it is!

⁠

Request AI-generated transcript

If you already have the transcript of the podcast, you can add it to our Studio, but first, you must generate a Musixmatch AI transcript. Click

here⁠

for instructions.

Paste the transcript

Once the AI transcript has been generated, inside the Editor click ‘Replace transcript’ in the top right of the toolbar

⁠

Paste your transcript into the text box. Paste spoken text only! (Speakers, episode title, any timestamps, and any indications like “[laughter]” or “[shouting]” should have already been removed)

⁠

⁠

⚠️ Do not select the ‘Tag speakers’ option if you don't have speakers formatted in your original transcript (more on this later)

Click Sync – the page will then load and refresh.

At this point you can close this window if you like (you will receive an email when your transcript is ready).

In about 5 minutes your episode should be ready, revealing your pasted transcript (you may need to refresh the page).

Should I tick ‘Tag speakers’?

When pasting your transcript you have two options. In the option above, your text should have been inserted without Speakers – so that from your original text it would have been impossible to tell who said what.

In the Editor, you would then go and insert the Speakers manually. The AI would have mostly recognised the different voices and separated them (into Speaker 1, Speaker 2, etc.).

⁠

⁠

You can then identify and add the actual names, manually making any necessary corrections.

Alternatively you can ‘code’ the Speakers into your transcript 👇

Using the ‘Tag speakers’ feature

In this second option you can ‘code’ your Speakers into your transcript, so that the Editor will tell them apart from the main text, and add your Speakers’ names automatically.

⁠

To format a Speaker in your original transcript, you need to use your own text editor (e.g. Google Docs or Microsoft Word).

The Speakers in your doc should be formatted like this: <<Speaker Name>> or <<generic>>

<<generic>> [for initial Ad (if there is one) or any generic speakers]

<<Marc Page>> What are we talking about today?

<<Kevin Red>> Today we are going to talk about podcasts!

<<Marc Page>> That's awesome.

<<generic>> [unknown/ irrelevant street interview] Hi, I was walking by when–

⚠️ Make sure that there is a Speaker tagged at least in the very beginning of the podcast

To tag a Speaker as "generic", use the format <<generic>>

Make sure you tick the ‘Tag speakers’ checkbox before you click ‘Sync’

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.