%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Amid the rapid iteration of artificial intelligence, the interaction experience of large models is undergoing a qualitative transformation from "text-based conversation" to "real-time emotional communication." On May 8th, Jieque Star, a leading company in the field of large models, officially announced its latest research achievement — the new real-time speech large model StepAudio 2.5 Realtime. The release of this model marks a new step in the naturalness and intelligence of domestic large models in voice interaction.
Deep Perception, Entering the "Human-Level" Interaction Era
Compared with traditional voice assistants, the core breakthrough of StepAudio 2.5 Realtime lies in its powerful "human-level" deep perception capabilities. It is no longer merely a rigidly identifying voice commands, but can sensitively capture subtle emotions and contextual changes in human conversations.
Through technological advancements, the model has achieved a dual leap in IQ and EQ. During the conversation, it can provide feedback that better meets emotional needs based on the user's tone and speaking speed, making the communication not just a one-way transfer of information, but more like a deep dialogue full of "human touch."
Flexible Customization, Creating a Personalized AI Persona
To meet the needs of different application scenarios, StepAudio 2.5 Realtime also introduces a highly flexible "personalized persona customization" feature. Whether you need a professional and steady workplace assistant or a humorous chat partner, developers or users can assign specific personality traits and language styles to the AI according to actual needs. This personalized capability will greatly expand the application boundaries of real-time speech models in education, entertainment, and office fields.
Full Launch, Domestic Large Models Accelerating Their Entry
Currently, Jieque Star has announced that StepAudio 2.5 Realtime is officially available in full. This means that developers and partners can immediately access and experience this cutting-edge technology.