iFlytek Releases SparkAudio 1.0, a Spark Speech Foundation Model
English text is being prepared.
At the 1024 Developer Festival, iFlytek announced the debut of SparkAudio 1.0, a Spark speech foundation model that integrates capabilities such as machine translation, speech recognition, and semantic understanding, and claims outstanding performance in real-time speaker separation, environmental understanding, audio understanding, and emotion recognition. The model has been fully launched in iFlytek Input Method 16.0, iFlytek Hearing, iFlytek Office Notebook, and iFlytek Translator, supporting arbitrary switching between Chinese and English and real-time speaker recognition. iFlytek also released the iFlytek AI Recording Ring, equipped with a 4 + 1 ring microphone array and Wi-Fi 6 transmission, claiming a comprehensive recognition accuracy rate of over 96% and that transcribing 2 hours of recording takes only 2 minutes.
Why read this
AI score 63
iFlytek has integrated its speech foundation model directly into products such as its input method and iFlytek Hearing, allowing readers to judge how voice interaction will be implemented in practice.
Topics
Body
科大讯飞首发星火语音基座大模型 SparkAudio 1.0：中英文任意切换、说话人实时识别，输入法里就能用
2026-10-22 15:02 IT之家 - 汪淼
IT之家 10 月 22 日消息，在今日下午的科大讯飞全球 1024 开发者节活动中，科大讯飞宣布首发星火语音基座大模型 SparkAudio 1.0。
SparkAudio 1.0 集成了机器翻译、语音识别、语义理解等能力，显著提升了基础语音能力。
模型宣称在实时说话人分离、环境理解、音频理解、情绪识别等方面“表现卓越”，推动人工智能向物理世界应用迈进。
官方通过一段电影片段的分析，展示了模型对声音内容、背景、说话人性别等的精准识别能力，以及场景判断的准确性。
SparkAudio 1.0 已在讯飞输入法 16.0、讯飞听见、讯飞办公本、讯飞翻译机全面上线，支持中英文任意切换、说话人实时识别。
IT之家注意到，科大讯飞还发布了一个“讯飞 AI 录音环”硬件设备，搭载 4 + 1 环麦阵列、Wi-Fi 6 传输，宣称综合识别准确率超 96%，进行 2 小时的录音转写仅需 2 分钟。