ggml/llama.cpp releases: b11946

TL;DR

The ggml/llama.cpp project added real-time conversation and transcription functionality on the /v1/realtime endpoint, enhancing interactive capabilities and user experience. This update is significant as it allows for more dynamic and responsive interactions with language models, potentially improving applications in chatbots and voice assistants.

Detailed Summary

The ggml/llama.cpp project has updated its server to include real-time conversation and transcription capabilities accessible via the /v1/realtime endpoint. This feature was co-authored by Xuan Son Nguyen from Hugging Face and assisted by Claude Opus 5.5, enhancing the application's interactivity and utility for users engaging in real-time text or audio interactions.

Key Points

• • server : add realtime conversation and transcription on /v1/realtime
• • examples : default the realtime client to the se