The Oct 23 2026 release improves the realtime API so audio streams finish only after all committed data is decoded.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org/llama.cpp project released version b11828 on Oct 23 2026. The main change is to the realtime API: a commit is now marked complete only after the audio buffer fully drains, preventing partial playback. The update also lists new builds for macOS, Linux, Windows, Android and more, including CUDA 13 and Vulkan support.
Developers can build voice‑enabled apps with llama.cpp that play back audio without cut‑offs.
Models
OpenAI's new ChatGPT Wallet lets its ‘dots’ agents purchase items for U.S. Pro subscribers using tokenized card data.
Models
The AI agent can place phone calls to cable companies, DMVs and restaurants, but many businesses still hang up on the synthetic voice.
Models
The new Gemini 4 Hydrogen model beats the larger Argon on speed, cost and several benchmarks, and is now available to developers and consumers worldwide.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
