● Covered by 1 source · 1 reportMedium impact1 neutral
Ollama for Mac adds local text-to-speech support with Gradium's Phonon models
Key points
- Ollama for Mac now supports text-to-speech.
- Uses Gradium's Phonon models for speech generation.
- Speech is generated in real time on local devices.
- MLX framework on Apple Silicon provides 35% faster generation.
Ollama Introduces Text-to-Speech on Mac
Ollama, an open-source platform for running AI models locally, has released an update for its macOS application that includes support for text-to-speech generation. This new functionality allows users to convert text into spoken audio directly on their Mac devices. Support for Windows and Linux versions of Ollama is expected to follow.
Integration with Gradium's Phonon Models
The text-to-speech capability is powered by Gradium's Phonon family of models. These models enable real-time speech generation, meaning users can hear AI-generated responses as they are produced, rather than waiting for a complete output. This marks Ollama's first venture into speech generation features.
Performance on Apple Silicon
On macOS, Ollama utilizes Apple's MLX machine learning framework, which is optimized for Apple Silicon's unified memory architecture. Tests on a MacBook Pro with M5 Max showed that Ollama achieved 35% faster speech generation compared to Gradium's own implementation, while maintaining the same word error rate as the reference implementation in Hugging Face Transformers.
Language and Voice Options
The Phonon models support five languages: English, French, German, Spanish, and Portuguese. Users can select from separate models for each language or use a multilingual model covering all five. Various voice options, including American and British English accents, are available depending on the chosen model.
Availability
The new speech models are available for Apple Silicon Macs running Ollama version 0.40.11 or later. Users can download compatible open-source AI models from repositories like Hugging Face to run them locally, enabling AI use without an internet connection or external server data transfer.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub ollama/ollamaReporting from
Ollama's Mac application now supports local text-to-speech generation using Gradium's Phonon models, with Windows and Linux support planned. This allows users to generate speech in real-time on their devices without an internet connection, leveraging Apple's MLX framework for faster performance.