Glossary
Neural voice
A text-to-speech voice generated by a deep neural network, producing more natural intonation and emotion than older concatenative or formant TTS.
Neural TTS models (Tacotron, FastSpeech, VITS and their successors) generate speech as a continuous waveform conditioned on text, speaker identity, and style tokens. The result has natural prosody, breath, and emotion — in many listening tests, people struggle to tell them apart from a human read.
Common attributes you can control: pitch, speed, language, accent, age, and emotion (calm, excited, sad, professional). In VlogMe you generate the voice in Audio Studio and can hand the same track to a talking avatar in Video Studio, so the lips follow exactly the delivery you chose.
