Uzha
Sign in
← Today's brief

Tools · Updated 24 Oct, 11:20 pm IST

Ollama v0.40.11 adds macOS speech and d3 decision models

Why it matters for readers: It lets you hear model replies on a Mac and experiment with models that make probabilistic decisions.

  • Ollama can generate and play speech on macOS, and apps can stream audio through an OpenAI-compatible /v1/audio/speech endpoint.1
  • The release includes d3 decision models in 2B, 4B, 9B, and 27B sizes that can classify, answer yes/no, or score options with probabilities.1
  • Users can run examples like 'ollama run phonon "Hello from Ollama."' and 'ollama run d3' to test speech and decision-model features.1
  • The changelog notes a new contributor, @SynapShift, with a first contribution referenced in the release notes.1
SaveAsk about this story
Report a mistake in this summary

Get a brief like this every morning

Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.

Get started