What happens when voice AI can understand more than just the words you say?

Join us in San Francisco for the launch of StepAudio 3, StepFun’s next-generation audio model family, with live demos showing how the models listen beyond words, keep pace with the rhythm of real conversation, and bring voice, sound, and context together in new ways.

We’ll show, not just tell. Xuerui Yang, Research Lead at StepAudio, will introduce StepAudio 3, walk through the thinking behind the new generation, and demo the models live before opening the floor for an audience AMA.

The evening will continue with a conversation featuring builders from PLAUD.AI, Coval, and more guests to be announced, focused on what it takes to turn advances in voice AI into products that work for real users.

♦️ Yijia Zhang, Partner & Head of AI Algorithm & Platform at PLAUD.AI♦️ Kobi Hudson, Founding Engineer at Coval

What to Expect

🎙️ A first look at StepAudio 3 and what this new generation unlocks⚡ Live demos of real-time voice and multimodal audio experiences💬 A live AMA with the StepFun audio model and product team🛠️ Candid lessons from leading voice AI builders🎁 Attend in person and get $100 in StepAudio API credits for your own apps and agents.🥂 Drinks, a light dinner, and time to meet founders, developers, researchers, and product leaders

Who Should Join

Founders, engineers, researchers, product leaders, enterprise teams, and investors building or exploring voice agents, audio models, multimodal products, intelligent devices, and human–AI interaction.

Agenda

6:00 PM, Check-in, light dinner, drinks & networking6:40 PM, StepAudio 3 introduction, live demos & AMA7:25 PM, Voice AI Leaders Panel & Audience Q&A8:10 ～9:00PM, Networking & product experience

About StepFun

StepFun is a leading foundation model company committed to the long-term pursuit of AGI. Its Step model family spans language, audio, multimodal, and reasoning capabilities.

StepFun also works closely with intelligent devices, with its models deployed across smartphones, automotive, and in-car agent experiences.