Audio Samples

Audio samples generated by two models A and B

Model A: T5_US_Accent_1
Trained on: LJ Speech Dataset
Description: This model has been fine-tuned to produce a more natural and expressive speech synthesis with a typical American accent.

Model B: T5_US_Accent_2
Trained on: LibriVox Dataset
Description: The second model has a more neutral tone, with a vibe reminiscent of the AI assistant "Friday" from the Iron Man series.

Note: None of these sentences were part of either training set.

For each sample, I've marked the model that sounds best with the text by adding (preferred) next to it.

Hi! I am so glad you called. What can I help you with today?
Model A (preferred)
Model B
It is a beautiful day outside. Don’t forget to take a break and enjoy it!
Model A (preferred)
Model B
Let us get started! This is going to be fun.
Model A (preferred)
Model B
System diagnostics complete. All core processes are fully operational.
Model A
Model B (preferred)
I have analyzed the data. Would you like a summary or a full report?.
Model A
Model B (preferred)
Engaging security protocols. Please stand by.
Model A
Model B (preferred)