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.
