Ollama for Mac adds support for local text-to-speech models

Ollama's macOS app now supports speech generation, starting with Phonon, a family of text-to-speech models from Gradium. Using Apple's MLX framework, it generates speech 35% faster than Gradium's own implementation; Windows and Linux support is coming soon.

• Phonon covers five languages: English, French, German, Spanish and Portuguese
• Speech generation is 35% faster than Gradium's implementation on an M5 Max MacBook Pro
• Requires Ollama 0.40.11 or later on Apple Silicon; Windows and Linux coming soon
• Speech is generated in real time as the response is produced