MONTY / PLAY
I challenged the new ChatGPT to a chat: the verdict on its new advanced voice
AI illustrationThe player connects to YouTube only after your click and may share technical data with Google. This choice is separate from AskMonty analytics. How it works
If this video cannot play here, use the YouTube link.
BEFORE YOU PRESS PLAY
What is discussed
AskMonty AI editorial noteSource consulted:
Montemagno tests ChatGPT’s advanced voice with tongue twisters, descriptions of Brighton, pitch simulations and different narrative styles. The conversation shows flexible intonation alongside repetitive responses, weak humor and difficulty meeting an exact duration. Requests involving volume, disagreement and language eventually lead to a discussion of the relationship between expressiveness, creativity and the constraints placed on the system.
Key points
- Similar content is tested with enthusiastic, skeptical, dramatic and instructional delivery.
- A requested thirty-second pitch lasts nineteen seconds, exposing a concrete limitation.
- The model tends to agree with its interlocutor and does not always describe its vocal capabilities clearly.
AI summary based on material from the linked source.
2glossary expressions documented here
Each expression counts once per item, even when repeated. The overall ranking covers the reviewed portion of the archive.
Open a symbol to discover its meaning. Checked against the source material. View source
The bald jokes
The hair and shampoo jokes are part of his self-deprecating humour about being bald.
Across the reviewed archive: 74 items
#3 in the ranking
Ping-pong / table tennis
A reference to his background: Marco says he played table tennis professionally when he was younger. This explains his mentions of paddles and his sporting experience.
Across the reviewed archive: 130 items
#1 in the ranking
