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

Canonical: https://theagenticweekly.com/news/ollama-v0-40-11-speech-d3-models · Evidence: Reported · First seen: 2026-10-26 03:48 UTC · Source published: 2026-10-24 00:30 UTC · Brief published: 2026-10-26 03:51 UTC · Updated: 2026-10-26 03:51 UTC · Author: Agentic Weekly

> 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.

## 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."
> (Ollama v0.40.11 release notes, https://github.com/ollama/ollama/releases/tag/v0.40.11)

> "brings vLLM Semantic Router's decision models to Ollama"
> (Ollama v0.40.11 release notes, on d3, https://github.com/ollama/ollama/releases/tag/v0.40.11)

## 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.

## Timeline

- Source published: 2026-10-24 00:30 UTC
- First seen by our watcher: 2026-10-26 03:48 UTC (via GitHub releases feed (watcher seed run)), 2.1 days after the source's timestamp
- Brief published: 2026-10-26 03:51 UTC

## Sources

- [Ollama v0.40.11 release notes (GitHub)](https://github.com/ollama/ollama/releases/tag/v0.40.11) (primary source) (fetched 2026-10-26)
- [Ollama docs: speech](https://docs.ollama.com/capabilities/speech) (fetched 2026-10-26)
- [Ollama library: d3](https://ollama.com/library/d3) (fetched 2026-10-26)

## Related

- [Ollama: verdict and setup guide](https://theagenticweekly.com/tools/ollama)
- [Ollama vs llama.cpp](https://theagenticweekly.com/compare/ollama-vs-llama-cpp)
- [Ollama vs Open WebUI](https://theagenticweekly.com/compare/ollama-vs-open-webui)
- [Alternatives to Ollama](https://theagenticweekly.com/alternatives/ollama)
- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)

## How to cite

Agentic Weekly, "Ollama v0.40.11 adds speech generation on macOS and the d3 decision models", published 2026-10-26 03:51 UTC, https://theagenticweekly.com/news/ollama-v0-40-11-speech-d3-models