Greg Isenberg's four-tool AI voice stack, powered by Google

Greg Isenberg uses four Google Gemini voice tools daily. First, Gemini 2.0 Flash Live — he treats it like a personal assistant he can call and ask things like 'How is my product launch going?' because it is connected to all his tools and runs his business in the background. Second, Gemini 2.5 Pro Transcribe — he records voice notes while walking, and it strips filler words and produces clean text, helping him capture and remember startup ideas. Third, Gemini 2.5 Flash Text-to-Speech — you can prompt it to generate a voice with a specific accent (like Brooklyn), useful for adding voice to mobile apps, such as welcoming new employees. Fourth, Gemini 2.5 Live Translate (speech-to-speech) — for real-time translation in business conversations, for example conducting a late-night deal in Mandarin in China, opening up new markets entirely.