Today, we are proud to launch Higgs TTS 2.5, the latest iteration of Boson AI’s audio model, designed to bring high-fidelity generation into production environments. Building on Higgs TTS 2, this release combines improved efficiency with the stability required for real-world deployment.

From October 24th through October 26th, 2025, Boson AI hosted its first large-scale Higgs Audio Hackathon in partnership with the Master of Science in Applied Computing (MScAC) program at the University of Toronto. With the recent release of our open-sourced Higgs TTS 2 text-to-speech (TTS) and automatic speech recognition (ASR) models, we opened the doors to over 200 innovators and developers, eager to explore, build, and most importantly, break our models.

Announcing Higgs TTS 2, our latest advancement in audio generation technology with enhanced multi-speaker and dialog capabilities. Now open source.

Since the release of Higgs Llama 2, we have received much positive feedback from the community. While we are amazed by the community's creativity in utilizing our model, we realize the importance of providing an automated benchmark to effectively evaluate large language model (LLM)'s roleplaying capability.

At Boson AI, we are working on intelligent agents that can serve as human companions and helpers. Today we are excited to share Higgs Llama 2 70B, a new model that significantly improves upon its predecessor. It narrows the gap to the very best proprietary models on benchmarks relevant for dialog interaction and understanding.