Voice AI Meetup: Introducing StepAudio 3 🚀

​Join the StepFun team for a first look at StepAudio 3, our next-generation audio model family designed to move voice AI beyond scripted exchanges—toward richer understanding, more natural real-time interaction, and expressive audio creation.

​We’ll show, not just tell: through a series of live demos, see how StepAudio 3 can listen beyond words, keep pace with the rhythm of real conversation, and bring voice, sound, and context together in entirely new ways.

​Xuerui Yang, Research Lead at StepAudio, will introduce the models, share the thinking behind this new generation, and take questions in a live AMA.

​After the demos, we’ll bring together builders from some of the most exciting companies in voice AI for a candid conversation about what it really takes to turn an impressive voice demo into a reliable product used by real customers. The full guest lineup will be announced very soon.

​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
🎁 Exclusive StepAudio API credits
🥂 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 & networking
6:40 PM — StepAudio 3 introduction, live demos & AMA
7:25 PM — Voice AI Leaders Panel & Audience Q&A
8:10 PM — Networking & product experience
9:00 PM — Event concludes

​By registering, you agree to receive occasional updates and marketing communications from StepFun. You can opt out at any time. Please note that photos and videos may be captured during the event for event-related and promotional use. if you do not consent, please let the event host know.