Notifications
Clear all
Topic starter
20/07/2026 9:50 pm
Hi everyone, new here. Been looking into ElevenLabs for a project. I've used some basic text-to-speech before, but the idea of cloning a voice for a whole audiobook is really interesting.
For those who've tried it, how accurate is it really? I'm thinking about consistency over a longer recording. Does it handle different emotions well, or does it sound a bit robotic in longer stretches? Any examples from personal projects would be super helpful.