Neural Voices in Text-to-Speech

Neural voices are the next generation in text-to-speech, using artificial intelligence to generate voices that sound closer to human voices and less robotic than text-to-speech of generations past.

We’ve added a range of neural voices to our text-to-speech library, supporting different languages and accents. You will find the new voices in the drop down, indicated with an ‘HQ’ for high quality.

Share Your Feedback:

Please fill in a one-minute survey and help us continue to provide high quality Vyond Studio experiences.