Ollama for Mac adds local text-to-speech with Phonon models

Ollama's Mac app now supports local text-to-speech generation through the new Phonon model family, with Windows and Linux support planned for the future. The open-source platform, which runs AI models locally on Apple Silicon via the MLX framework, reports 35% faster speech generation than Gradium's reference implementation on a MacBook Pro with M5 Max. Phonon supports five languages and multiple accented voices. Available now for Apple Silicon Macs running Ollama 0.40.11 or later, the feature generates audio in real time, allowing users to hear responses as they are produced. Users can download Phonon directly through Ollama.