OpenAI Voice Engine

About OpenAI’s Voice Engine is a text-to-speech tool which can create realistic voices from just a 15-second audio sample. It is notable that a small model with a single 15-second sample can create emotive and realistic voices. To ensure responsible use testers must get clear consent from voice providers, avoid creating user-generated voices, and inform listeners that the voices are AI-generated. Status & Access Voice Engine has remained in limited preview since its 2024 announcement. OpenAI has been cautious about broader deployment due to responsible AI considerations around synthetic voice generation, particularly concerns about voice cloning and impersonation risks. ...

March 29, 2024 · 1 min · James M