Ollama adds Phonon speech models for macOS

Ollama now supports Phonon, a 40M text‑to‑speech model from Gradium, streaming in five languages with dozens of voices, over 100× faster than real time; on a MacBook Pro M5 Max it is 35% faster than Gradium’s runtime.

Benchmarks are the company's own; not independently verified.

Why it matters

Ollama's Phonon adds speech generation in five languages; plan product features that include voice output using the OpenAI‑compatible endpoint.

For product managers

For your product

What does this mean for your product?

Try it on your product

Read at Ollama

More from this issueAll AI news from 26 Oct →

OpenAI launches Decisions API, entering Jev decision‑model marketAvailable now

SpaceX secures $40 billion debt financing to buy AI GPUs

OpenAI offers up to 90% discounts to poach Anthropic's biggest customersAvailable now

Hugging Face Releases Carbon‑X 14.8B Open DNA Language ModelAvailable now

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Request an invite See how it works