Agentic WeeklyGet the weekly

Ollama v0.40.11 adds speech generation on macOS and the d3 decision models

Release Ruler for this brief: marked at its publication date, Oct 26, 2026, among the AI models we track.

Ollama v0.40.11 can generate speech on macOS, through ollama run or an OpenAI-compatible audio endpoint, and adds the d3 family of decision models in 2B, 4B, 9B and 27B sizes.

By Agentic Weekly · Evidence: Reported · How we work

First seen
(via GitHub releases feed (watcher seed run))
Source published
(we saw it 2.1 days later)
Brief published

What changed

  • Speech: Ollama can now generate speech on macOS. ollama run plays text or a chat model's reply aloud as the audio is generated.
  • Apps can stream audio through the OpenAI-compatible /v1/audio/speech endpoint.
  • The release's example is ollama run phonon "Hello from Ollama.", and it links to a speech page in the Ollama docs.
  • New d3 models bring vLLM Semantic Router's decision models to Ollama: give a model text, structured state or an image and ask it to classify, answer yes or no, or score options with probabilities.
  • The d3 family comes in 2B, 4B, 9B and 27B sizes.
  • The release lists one new contributor and no other items.

In the source’s words

“Ollama can now generate speech on macOS.”

“brings vLLM Semantic Router's decision models to Ollama”

What we have not verified

  • We did not run this release, so we cannot say how speech or the d3 models perform.
  • The release says speech works on macOS; support on Linux and Windows is not stated there.
  • Model quality, memory needs and licensing of d3 are not covered by the release notes.

This brief is Reported: written from the sources below, not from running the release ourselves.

Sources

Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/ollama-v0-40-11-speech-d3-models.md

Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.