I recall the author saying they're not a native English speaker, and preferring international intelligibility over regional voice-over, plus the production convenience while traveling and script writing without a quiet audio recording environment. See around 7 min mark:

The most common question on my channel - Core Dumped
- https://youtube.com/watch?v=FlOVA8NLGDQ

[–] HappyFrog@lemmy.blahaj.zone 7 points 11 months ago (1 children)

Don't get me wrong, I like the channel, I just find the voice AI produces to be very grading. I like that he can produce the videos he likes, and I'd rather have a AI voice than no voice at all.

[–] ruffsl@programming.dev 4 points 11 months ago (1 children)

I've been using TTS systems for decades with accessibility use cases, so other than quality audio books that necessitate a skilled performing narrator, I no longer mind.

In fact, I prefer legacy Bayesian phonetic models over the newer convolutional and recurrent neural networks, as their hard consonants and robotic consistency in pronunciations and intonation are much easier to listen and discern at higher words per minute, like at 3x or 4x natural speech rates for everyday blind reading, as compared to modern mumbling/slurring of syllables or artificial stridor and other breathy sounds.

[–] HappyFrog@lemmy.blahaj.zone 2 points 11 months ago

I use tts myself to read scientific papers, but I use voices that sound more robotic. I find it easier on the ears.

load more comments (2 replies)