iFLYTEK used its 2026 Global 1024 Developer Festival to set out a path from voice interaction to multimodal interaction and then to embodied multimodal interaction for robots. Two releases anchor that plan: the SparkAudio 1.0 speech foundation model and Robot Super Brain Platform 3.0, according to Sina Tech, IT Home and a transcript of chairman Liu Qingfeng's keynote posted by iFLYTEK on Tencent News.
SparkAudio 1.0 brings machine translation, speech recognition and semantic understanding into one base model, so the tasks can learn from each other. Beyond recognition, simultaneous interpretation and voice interaction, iFLYTEK says it handles real-time speaker separation, environmental sound understanding, audio understanding and emotion recognition. In a noisy street, the company says, it can pick out horns, vendors and tire noise, separate overlapping voices and infer the surroundings from sound.
iFLYTEK's technical report adds detail. The model pairs a 0.65-billion-parameter dense audio encoder with a 30B-A3B mixture-of-experts language model and was trained on 13 million hours of audio plus large text corpora. It supports speech recognition in 99 languages and 202 dialects, and was trained on domestic accelerators including Huawei Ascend 910B and Hygon BW1000 chips. Liu named three technical changes: a semi-supervised audio decoder that raises accuracy by 20%, dynamic segmented end-to-end modeling that cuts response time by 15%, and dual-paradigm collaborative decoding that lowers cost by 60%. These figures are iFLYTEK's own, and the report says instruction following and complex audio reasoning still need work.
SparkAudio 1.0 is already live in iFLYTEK Input Method 16.0, iFLYTEK Hearing, its smart notebooks and translators. The company also showed an AI recording ring that attaches magnetically to the back of a phone and can transcribe two hours of audio in two minutes.
For robots, iFLYTEK introduced Spark embodied multimodal interaction technology. It targets dynamic noise reduction in complex spaces, recognizing which of several people is addressing the robot, planning speech and motion together, such as waving while saying goodbye, and starting conversations when the camera spots something relevant.
Robot Super Brain Platform 3.0 packages that work. On the hardware side it includes the Spark super brain board, a multimodal interaction module and an embodied AI development kit. On the software side, an embodied multimodal interaction harness coordinates device and cloud, and front-end and back-end tasks, so a robot can keep chatting while it carries out jobs in the background. The platform supports modular, configurable customization for different industries. At the event, iFLYTEK demonstrated it in an unstaffed, 24-hour robot-run store.
SEE ALSO: iFLYTEK Launches Spark X2.6 · iFLYTEK Ships Spark-ASR-2.0