We provide 567 lifelike TTS and NTTS voices in 42 languages.
Adjust attributes such as pitch, volume, rate of speech, pauses and more. Use a child voice for content aimed for children or use a voice specific to your dialect. All of these great things allows you to bring a rich end user experience.
Most of our neural voices uses WaveNet, "a deep generative model of raw audio waveforms. WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%." - DeepMind.com
We provide plenty of non-neural voices, varying from Standard to Exclusive voice class. Don't get us wrong, these voices are great as well!