Read our blogs, tips and tutorials
Try our exercises or test your skills
Watch our tutorial videos or shorts
Take a self-paced course
Read our recent newsletters
License our courseware
Book expert consultancy
Buy our publications
Get help in using our site
485 attributed reviews in the last 3 years
Refreshingly small course sizes
Outstandingly good courseware
Whizzy online classrooms
Wise Owl trainers only (no freelancers)
Almost no cancellations
We have genuine integrity
We invoice after training
Review 30+ years of Wise Owl
View our top 100 clients
Search our website
We also send out useful tips in a monthly email newsletter ...
Using Google NotebookLM to generate your own podcasts Part three of a four-part series of blogs |
---|
Is there any limit to what AI tools can do? Google's NotebookLM tool summarises documents, websites and other sources using the medium of podcast.
|
In this blog
I wasn't 100% successful with converting my podcast to good old British English, but I thought somebody might find it useful to see the sort of hoops that you might have to jump through to change the accents or language of a generated podcast (sadly, NotebookLM currently only generates audio overviews in American English).
I was hopeful that this would do everything in one fell swoop, and certainly ChatGPT implied it would:
I was really excited that this was going to work!
Everything was looking rosy:
Problem sorted! Or was it?
Unfortunately the results sounded like a Chinese person imitattng a Teletubbie, and made no sense whatsoever.
I pointed this out to ChatGPT, and it said that it would take longer and use an external translation service - but the results were just as bad after this.
ChatGPT eventually suggested I transscribe the audio using a service like Whisper, Sonix, Otter or Rev. After a bit of research Rev seemed simple to use, and I got it to transcribe my podcast:
The start of the podcast, successfully transcribed. You can then export this as a PDF.
For the final part of the process, research (and ChatGPT) suggested using ElevenLabs, Resemble AI or PlayHT to regenerate the podcast, but using English accents. After some more research I chose PlayHT to recreate the podcast:
I couldn't find how to join the paragraphs together, but I felt this was solvable given time.
There were many voices to choose from - here are some of the female British ones, to give an idea:
I went with Sarah (not shown above).
At this point I could have downloaded the recording had I upgraded to a paid plan, but I felt I'd got closer enough to proving that my goal was possible!
Parts of this blog |
---|
|
Some other pages relevant to the above blogs include:
Kingsmoor House
Railway Street
GLOSSOP
SK13 2AA
Landmark Offices
99 Bishopsgate
LONDON
EC2M 3XD
Holiday Inn
25 Aytoun Street
MANCHESTER
M1 3AE
© Wise Owl Business Solutions Ltd 2025. All Rights Reserved.