“The app can clone their voice from just 10 seconds of audio... the app will clone their voice and then put that into a text-to-speech board”
VB
Voice Back Riya Jain
How I Built This with Guy Raz ·
“The experts used almost an hour of samples to develop a personalized model of the politician's authentic voice.”
TED Tech · Democracy in the Age of AI (2/5): When AI can fake reality, who can you trust? | Sam Gregory
Play from 6:11
6:11
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
built a personalized voice model from almost an hour of audio samples to test a politician's clip
almost an hour of samples
Said nearby on the same subject
“I read books in like 24 hours or 48 hours because I taught myself how to like speed read or listen to audio books at like two or three times.”
SH
Sasha Hamdani
Habits and Hustle ·
“I gave Claude a raw file… and said, make it sound like that… it built an audio engine in like, what, 20 to 30 minutes.”
SR
Stephen Robles
The Vergecast ·
“We would make people go through tests they would submit work samples we would go through multiple rounds of interviews”
JS
Jaspreet Singh
Afford Anything | Get Smarter With Money ·
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.