StepFun has released StepAudio 3 and rolled out five voice models at once: Realtime, ASR, TTS, Gen, and Music. In two voice evaluations tracked by Artificial Analysis, StepAudio 3 Realtime ranked first in both categories. It scored 98.9% in Conversational Dynamics, ahead of Qwen Audio 3.0 Realtime Plus at 98.4% and GPT-Realtime-2 High at 95.3%. It also posted 99.7% in Speech Reasoning, taking the top spot there as well. According to the benchmark descriptions cited in the source, Conversational Dynamics measures how well a model handles pauses, turn-taking, user interruptions, and short acknowledgements, while Speech Reasoning tests whether a model can directly understand audio and complete reasoning tasks. In ASR, StepAudio 3 recorded a 1.7% WER on Artificial Analysis' non-streaming speech recognition leaderboard, tying for first with Fun-Realtime-ASR-preview. StepAudio 3 Gen also supports one-shot generation of vocals, sound effects, ambient audio, and music, with scene-level arrangement. All five models have now been added to StepFun's voice product lineup.
StepFun has released StepAudio 3, rolling out five voice models in one batch: Realtime, ASR, TTS, Gen, and Music.
In two voice evaluations from Artificial Analysis, StepAudio 3 Realtime ranked No. 1 in both. The model scored 98.9% in Conversational Dynamics, ahead of Qwen Audio 3.0 Realtime Plus at 98.4% and GPT-Realtime-2 High at 95.3%. It also scored 99.7% in Speech Reasoning, which also placed it first.
According to the source, Conversational Dynamics mainly measures whether a model can handle pauses, turn-taking, user interruptions, and short acknowledgements such as 「嗯」 and 「对」. Speech Reasoning tests whether the model can directly understand audio input and complete reasoning tasks.
On the ASR side, StepAudio 3 reached a 1.7% WER, or word error rate, on Artificial Analysis' non-streaming speech recognition leaderboard, tying for first with Fun-Realtime-ASR-preview.
StepAudio 3 Gen can also generate vocals, sound effects, ambient sound, and music in a single pass, then arrange them under one scene. All five models have now entered StepFun's voice product lineup.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
