Type any script. Hear it back in that Sacramento-LA indie-director conversational register — bright mid-alto, slightly nervous-energetic, sentences that double back on themselves the way a director thinks out a scene in real time. Lady Bird warmth, Barbie-press-tour intelligence. Studio-quality MP3 in under a minute. No software to install. Built on HyperVoice, our proprietary neural TTS engine.
Greta Gerwig's speaking voice is a Sacramento-LA-New-York hybrid mid-alto that talks the way she directs — thinking out loud, doubling back, self-correcting in real time. The voice is bright. The cadence is conversational and slightly faster than a typical leading-actress register, because she is not, in fact, primarily a leading actress. She is a director who acts when asked. That distinction shows up in every sentence.
TaskAGI's Greta Gerwig AI voice generator runs on HyperVoice, our proprietary text-to-speech engine. The model captures that director-conversational register specifically — the Sacramento baseline polished by mumblecore-NYU film-school overlay, the half-finished-clause cadence she uses on Criterion Closet picks and director commentary, and the bright intelligence that runs every Barbie-era press appearance.
Four presets cover modes. Conversational is the default Criterion-Closet-style podcast register. Director-Commentary opens slightly for film-criticism and behind-the-camera narration. Press tightens for red-carpet and awards-cycle reads. Essay slows the cadence for long-form film-critic-essay narration.
Creators reach for this voice when a script needs indie-cinema warmth with film-school intelligence underneath. Film-criticism YouTube essays. Director-commentary tracks. Indie-cinema documentary cold-opens. Barbie-era brand voiceover (if framed as cultural-criticism). The voice does work that a generic young-female TTS cannot do because it carries a specific learned literacy — the literacy of a director who reads as much as she shoots.