Ollama v0.40.11 adds speech generation on macOS and the d3 decision-model family
Ollama
Ollama v0.40.11, published October 24, generates speech on macOS: ollama run plays a text or chat model reply aloud as audio streams, and apps can stream through the OpenAI-compatible /v1/audio/speech endpoint. It also adds d3, vLLM Semantic Router's decision models in 2B, 4B, 9B and 27B sizes, which take text, structured state or an image and classify, answer yes/no, or score options with probabilities.
Why it matters
Brings a serving-side router and classifier family into the local runtime, next to TTS.
Importance: 2/5
Notable minor release: new capability class plus macOS TTS.
Sources
official
Ollama v0.40.11