AI Voice is a computer generated voice powered by machine learning and can generate speech from text with natural intonation and real accents. AI Voices are created by machine learning models that process hundreds of hours of voice recordings from real voiceover artists and then learn to speak based on the audio recordings. Today AI Voices are used in several applications due to their natural-sounding tone.

Oct. 2, 2023

All our AI Voices support SSML features - rate, pitch, volume and pronunciations. You can add custom pauses for different punctuation marks to create a more natural speaking tone. Adjust the pitch of the voice to make it sound more deeper or child-like. The speaking rate allows you to increase or decrease the speed of voice. With our pronunciations library you can save custom pronunciations and use them whenever you create speech.

Oct. 2, 2023

Yes, we do offer a free version that allows you to preview all the available voices and convert a few words to audio.

Oct. 2, 2023

Extremely real. Our voice models are built to generate speech exactly like a human, including natural pausing, breathing, and using filler words to mimic a real human being. Give our latest voice model, PlayHT2.0 a try and listen to the generated voice yourself!

Oct. 2, 2023