Models & Labs
Ollama adds local TTS with Phonon and MLX acceleration
Ollama Bloghigh confidence
Why it matters
- →Local TTS is now natively supported in Ollama, removing the need for separate inference servers.
- →MLX acceleration on Apple Silicon delivers superior throughput compared to the model vendor's own runtime.
- →OpenAI-compatible API endpoints allow existing audio generation code to work with local models.
Ollama has released version 0.40.11, adding native support for text-to-speech through Gradium’s Phonon model. The implementation leverages Apple’s MLX framework on macOS, achieving a 35% speed advantage over the vendor's own runtime on M5 Max hardware while maintaining high accuracy. The feature supports multiple voices, streaming audio output, and an OpenAI-compatible API endpoint for easy integration. Windows and Linux support is scheduled for future releases.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1OpenAI Unveils New Voice Models for ChatGPT
TechCrunch AI · July 8, 2026 · Background
- 2Meta's Muse Glimmer Model Now Available
Ollama Blog · August 10, 2026 · Related
- 3BreezeTTS2: Real-time local voice synthesis
Sam Witteveen · August 31, 2026 · Related
- 4Guide to Running Local AI Models Offline
Lev Selector · September 20, 2026 · Background
- 5Transformers adds native GGUF support for Apple Silicon
Hugging Face Blog · September 22, 2026 · Background
- 6Ollama adds Jev-style decision models
Ollama Blog · September 29, 2026 · Related
- 7Hugging Face launches objective Open TTS Leaderboard
Hugging Face Blog · September 30, 2026 · Background
- 8GitHub Copilot CLI v1.0.94 adds local Ollama model discovery
GitHub Changelog · October 7, 2026 · Background
What happened next
- 9llama.cpp adds Soprano TTS support
llama.cpp Releases · October 24, 2026 · Related
- 10llama.cpp adds LiquidAI LFM3-Audio and Omni support
llama.cpp Releases · October 28, 2026 · Related
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe