# llama.cpp b12426 adds support for two speech models

> The release adds Higgs v3 speech-to-text and VibeVoice-ASR support to llama.cpp’s media-handling tools.

Oossa · 2026-11-15 · https://oossa.com/en/llama-cpp-b12426-adds-support-for-two-speech-models

The ggml-org team has released llama.cpp b12426, adding support for Higgs v3 speech-to-text and VibeVoice-ASR in its media-handling code. Speech-to-text converts spoken audio into written words.

The release page also provides downloadable builds for macOS, iOS and several Linux systems. It does not specify which model versions or usage limits apply to the new audio support.

## The facts

- The audio-support change is listed as pull request #32329.
- Builds are listed for macOS Apple Silicon and Intel, iOS, and several Linux platforms.

## Why it matters

Developers using llama.cpp can try its new support for these speech models, though the release notes do not explain the setup requirements or supported model details.

## Sources & references

1. [ggml-org/llama.cpp b12426](https://github.com/ggml-org/llama.cpp/releases/tag/b12426) – llama.cpp, 2026-11-15

Last updated: 2026-11-15
