Type any script. Hear it back in that casual, slightly-tired, Connecticut-Gen-Z TikTok speaking voice — the one that built the largest dance-creator audience on the internet and made the way you talk to your phone into a format. Studio-quality MP3 in under a minute. No software to install. Built on HyperVoice, our proprietary neural TTS engine.
Charli D'Amelio's TikTok speaking voice is, in its own way, an enormous audio invention. It is the voice that made the storytime format — phone-up, eye-contact, slight-uptalk, casual-filler — into a structure that millions of creators have copied. The voice itself is light, mid-register, Connecticut-suburban, slightly tired, with the verbal-filler density that signals I am being honest with you right now, this is not produced.
TaskAGI's Charli D'Amelio AI voice generator runs on HyperVoice, our proprietary text-to-speech engine. The model captures the specific signatures: the rising intonation on declarative statements, the long like placeholder before a noun, the way she trails the end of a sentence into a question even when it isn't one, the slight Connecticut nasal warmth.
The four style presets target the four major content modes. TikTok is the default high-energy GRWM mode. Storytime slows it down, pulls in the verbal-fillers, and adds the conversational backtracks that make a long-form story feel candid. Reaction is the pause-rewatch-explain energy. Vlog is the calmer mid-day-in-the-life mode.
Creators reach for this voice when a script needs to sound like a Gen-Z creator actually wrote it. Not a polished newscaster reading TikTok captions. Not a copywriter pretending to be casual. The verbal fillers, the uptalk, the conversational backtracks are features of the format — and the model leans into them rather than sanding them out.