Ollama launches text-to-speech, premiering Phonon
The story so far
Ollama has added text-to-speech capabilities, with the first integrated voice model being the Gradium Phonon mini TTS model family. This feature currently only supports Apple Silicon Macs on macOS, with Windows and Linux support listed as 'coming soon'. Use requires downloading Ollama 0.40.11 or higher version. The 40M Phonon model is released under the CC BY-NC 4.0 license, strictly for non-commercial use. It is compatible with OpenAI's /v1/audio/speech interface, and existing code using the OpenAI SDK can call it by simply changing the base URL. Ollama states that on macOS, this feature runs offline using Apple's MLX framework, with data not needing to be uploaded to the cloud. Official tests show that on a MacBook Pro equipped with the M5 Max chip, Phonon achieves speech generation speed 35% faster than Gradium's own implementation, while maintaining word error rates comparable to Hugging Face Transformers' reference implementation.
AI-written from the reports · Updated 23 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- ITHome · AIOllama Mac version adds offline AI voice generation: data stays within the door, speed up to 35% faster than the original solution.
Ollama announced on October 24 that its Mac app officially supports text-to-speech (TTS) generation. The first supported voice model is the Phonon series developed by Gradium, which allows users to run it without relying on cloud services on Apple Silicon Macs. On MacBook Pro equipped with the M5 Max chip, Phonon voice generation speed is 35% faster than Gradium's own implementation and supports real-time voice generation.
- Ollama BlogFeaturedSpeech models in Ollama
Ollama adds text-to-speech capability, the first integrated speech model is the small TTS model family Phonon from Gradium, currently supporting macOS, Windows, and Linux with support for Linux to be released soon.