For the first time, developers can also instruct the text-to-speech model to speak in a specific way—for example, “talk like a sympathetic customer service agent”—unlocking a new level of customization for voice agents. OpenAI . fm is a platform designed for developers to experiment with the latest text-to-speech model available in the OpenAI API. This interactive demo allows users to generate realistic speech from text inputs, showcasing the capabilities of OpenAI ’s advanced audio processing technology. OpenAI . fm offers an interactive demo for exploring OpenAI ’s advanced text-to-speech technology, allowing users to convert text into natural-sounding audio with ease. On March 20, 2025, OpenAI set the developer community buzzing with a low-key technical livestream. The event unveiled OpenAI.fm , a brand-new voice technology platform, alongside three cutting-edge speech-to-text and text-to-speech models that form the technological backbone of the platform. OpenAI.FM Introduction OpenAI 's audio lineup includes two speech-to-text models and one text-to-speech model: gpt-4o-transcribe (speech-to-text), gpt-4o-mini-transcribe (lightweight speech-to-text), and ...
