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