Meet some of our 315+ voices.
Each voice has a distinct character and a set of emotion styles. Hit play to compare them.
A calm, low, handsome male voice. Suits mature narration.
A fresh, lively young man's voice with a boyish tone. A prototype voice released free to use.
A soft, gentle young female voice with a calm, slightly mature delivery.
A lively, mischievous girl's voice. Expressive across 6 styles, from sweet to teasing.
A calm girl's voice with a watercolour softness. 7 styles, including joy and sadness.
An honest, bright girl's voice (the orange-haired character), with a gentle delivery.
A realistic voice of a woman in her twenties. 5 styles, suited to natural spoken lines.
A cat-like, coaxing girl's voice. Switch the mood with 4 styles, including sleepy and wistful.
A lively junior-high-school girl's voice. Suits brisk narration.
A cool, stylish cyber-style voice. A wide emotional range across 5 styles.
A gentle classmate-like voice (the pink-haired character). Calm and friendly narration.
An elegant, refined young woman's voice. Clear and calm, suited to reading aloud.
A bright middle-aged male baritone. 7 styles, from calm narration to shouting.
Trained on professional 96 kHz studio recordings (noise and echo removed) and the 424-sentence ITA corpus.
A female voice with 5 styles: Normal, Anger, Joy, Playful and Surprise.
A middle-aged male voice.
The voice model of kokuren (@wangoroge333).
A voice model meant as a general-purpose female voice.
A male voice model.
A natural voice of a woman in her twenties (from the RiaboVC voice changer).
The voice of Hakimite Reku, a self-styled 'tech monster' VTuber.
A natural voice of a woman in her twenties (from the RiaboVC voice changer).
A natural voice of a woman in her twenties (from the RiaboVC voice changer).
The speech model of Rasetsun from the Kozukata Gakuen project.
A voice model recorded acting as an anonymous interviewee.
A voice model recorded acting as an elderly person.
A natural voice of a woman in her twenties (from the RiaboVC voice changer).
Rokugen Ereki's speech model, made for AivisSpeech.
Sawabaru Genjirō (CV: Kirio Furuyama), an impatient, mischievous cat. The extra noise is intentional.
A voice model made from the streams of the VTuber Shōjō Hakase (Dr. Shōjō).
A natural, unpolished voice recorded by its creator.
Found a voice you like?
Install Yomite to start using them right away.
Download on the App Store Google Play (Android)