AI News Feed
Market watch
Engadget guide maps out what the PS5's USB ports can do beyond charging a controllerResearchers Confirm In-the-Wild Exploitation of Critical PHP2Shell FlawsOpenClaw creator says he spent $10 million in tokens in one month at OpenAIAnthropic Files for Nasdaq IPO as Cramer Warns Mega-Listings Could Strain MarketBottoms Seeks Georgia Data Center Pause; Court Unseals New Comey ChargesHalide Releases First iPhone Duo Update With Pose-Specific Camera Controls
Engadget guide maps out what the PS5's USB ports can do beyond charging a controllerResearchers Confirm In-the-Wild Exploitation of Critical PHP2Shell FlawsOpenClaw creator says he spent $10 million in tokens in one month at OpenAIAnthropic Files for Nasdaq IPO as Cramer Warns Mega-Listings Could Strain MarketBottoms Seeks Georgia Data Center Pause; Court Unseals New Comey ChargesHalide Releases First iPhone Duo Update With Pose-Specific Camera Controls
Products & Applications

Ollama’s Mac App Adds Local Text-to-Speech Support With Phonon Models

Ollama’s Mac app now supports local text-to-speech, starting with Gradium’s Phonon models; Windows and Linux support is coming.

AI News Feed · 2026-10-27 08:40

According to 9to5Mac, Ollama is a platform that lets users download and run open AI models locally on Macs, Windows and Linux, or access more powerful models through the cloud. The project is open-source and has nearly 185,000 stars and about 18,600 forks on GitHub. On macOS, Ollama uses Apple’s MLX, an open-source machine learning framework that uses Apple Silicon’s unified memory architecture to run supported AI models faster and more efficiently.

Users can download compatible open-source AI models from repositories such as Hugging Face and run them directly on their Macs. That allows them to use AI without an internet connection or sending data to external servers, although performance and the size of the models they can run depend heavily on their Mac’s hardware.

Ollama said the first speech model is Phonon, a family of small, state-of-the-art text-to-speech models from Gradium. The company described the feature as real-time speech generation, meaning users can listen to AI-generated responses as they are being produced rather than waiting for the entire response to finish.

“Ollama can now turn text into speech. The first speech model is Phonon, a family of small, state-of-the-art text-to-speech models from Gradium. Speech models are now available for macOS, with Windows and Linux support coming soon,” Ollama said.

The platform said that, thanks to Apple’s MLX framework, it achieved 35% faster speech generation than Gradium’s own implementation in tests on a MacBook Pro with M5 Max, while matching the word error rate of the reference implementation in Hugging Face Transformers. Phonon supports five languages—English, French, German, Spanish and Portuguese—with separate models for each language, as well as a multilingual model that supports all five. Users can also choose from a variety of voices with different accents, including American and British English, depending on the model.

The new speech models are available now for Apple Silicon Macs running Ollama 0.40.11 or later. Users can get started by downloading Phonon directly through Ollama. Ollama also provided audio samples and instructions, including code examples for using the models through its API.