Boson AI's new audio generation model is out: emotionally expressive voice, long form audio, multi-speaker cloning, directable audio (e.g. music, laughter), trained on 10M+ hours of audio, and best of all, open source. https://t.co/fvRBRmhorA - @boson_ai @sxjscience @mli65

We're looking for a community supporter for #HiggsAudio to help us answer questions and help the community build things. This is a great part time job if you're a student. Message me if you want to help.

We haven't trained Higgs Audio for Japanese yet ... but stay tuned.

Innovation and high quality speaks for itself, @boson_ai #higgsaudio v2 is a big hit! treading on top 5 on @huggingface this week.

NEW: Higgs Audio V2 from @boson_ai open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody

New TTS bomb dropped on Hugging Face. It has multispeaker support and the output quality looks amazing 🤯

#HiggsAudio V2 by @boson_ai is now the #1 trending audio model on @huggingface - try it out on https://t.co/AHCHOBM0UL

I'm at #ICLR2025 in Singapore. @boson_ai is hiring in Santa Clara and Toronto to help us build amazing audio models for communication. https://t.co/BWrWbXz8OV

Higgs Audio Generation benchmarks @boson_ai

Higgs Audio Understanding benchmarks @boson_ai

At @boson_ai we are excited to introduce Higgs Audio Understanding and Higgs Audio Generation — two powerful tools designed to build customized AI agents tailored for diverse audio understanding and generation needs. Check it out at

Here's a plug for @manzilzaheer and team at Google: they released Gemma embeddings on Huggingface. Good job!

Excited to share Higgs-V2, improved both general and roleplaying abilities. The performance boost comes from the in-house built reward model. More at https://t.co/mgtQe7heOK

We are #hiring for ML Modeling Scientist at https://t.co/IqUdkb09TM. Message me if you're interested in joining our team. We are attending 2024 International Conference on Machine Learning if you would like to meet!

Announcing Higgs Llama v2 - the state of the art for human machine interaction. Check it out at

Obviously trained on Llama-3 base (Xitter won't let me edit past tweets).

Proud to release the first LLM from @boson_ai. Higgs-Llama-3-70B, built for characters and gameplay, trained on Boson-3 base. With great MMLU-Pro performance.

I'll be giving a talk on @AutoGluon 1.0 at @AutomlSeminar on Feb 15th at 9 AM PST, come listen in on the latest innovations taking place in the world of AutoML!

🏅AutoGluon was used in the 2nd place solution of @Kaggle's latest ML competition out of 3777 competitors! Embrace the AutoML Revolution! 🚀 https://t.co/KXZJWY2pH3

I am actively looking for ELLIS Ph.D. students to join my lab at @ISTAustria Please spread the word!