88Z AI, 15 September — StepFun has released the StepAudio 3 series of voice large models, covering five areas: real-time interaction, speech recognition, speech synthesis, full audio generation, and music creation. The Realtime model topped the global real-time voice interaction rankings with a comprehensive score of 98.9%, while the ASR model achieved a word error rate of just 1.7%, tying for first place. Several models in the series have achieved leading global positions on the Artificial Analysis leaderboard, demon
At a glance
- The StepAudio 3 series includes five models covering scenarios from real-time conversation to music creation
- The Realtime model ranks first globally with a 98.9% score, while the ASR model ties for first with a 1.7% word error rate
The update
StepFun has officially launched the StepAudio 3 series of voice large models, which includes five specific models: Realtime, ASR, TTS, Gen, and Music. This product matrix comprehensively covers core application scenarios such as real-time conversation, speech recognition, human-level speech synthesis, full audio generation, and music creation. In terms of performance, the StepAudio 3 series has achieved significant breakthroughs. The Realtime model topped the global rankings for real-time voice interaction with a comprehensive score of 98.9%. Meanwhile, the ASR model achieved a word error rate of only 1.7%, tying for first place with other top-tier models. Reports indicate that several models in this series rank first globally on the authoritative Artificial Analysis leaderboard, highlighting their leading position in the field of voice technology.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 阶跃StepFunSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.