阶跃星辰发布 StepAudio 3 系列 5 款音频模型
Introducing StepAudio 3, our new family of 5 audio models for real-time voice, speech recognition, speech generation, audio generation and music.
阶跃星辰发布 StepAudio 3 系列 5 款音频模型，覆盖实时语音、语音识别、语音生成、音频生成和音乐。其中 Realtime 在 Artificial Analysis 的 Conversational Dynamics（98.9%）和 Speech Reasoning（99.7%）两项排名第一，ASR 的 WER 为 1.7%，与榜单最佳结果持平。官方称可用于构建能处理打断、边说话边推理并调用工具的语音智能体，现已开放 Voice AI Lab 和 API。
正文
当前显示原文，中文全文译文尚未就绪。
Introducing StepAudio 3, our new family of 5 audio models for real-time voice, speech recognition, speech generation, audio generation and music.
Realtime ranks #1 on Artificial Analysis for both Conversational Dynamics (98.9%) and Speech Reasoning (99.7%). ASR reaches 1.7% WER, matching the best result on the leaderboard.
Build voice agents that handle interruptions, reason while speaking, and call tools. Transcribe speech, generate expressive voices, and create full audio scenes and music.