iFlytek Releases SparkAudio 1.0, a Spark Speech Foundation Model
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 · AI translation
iFlytek Debuts SparkAudio 1.0, the First Spark Speech Foundation Model: Seamless Chinese-English Switching, Real-Time Speaker Recognition, Usable Right in the Input Method
2026-10-22 15:02 IT Home - Wang Miao
IT Home, October 22: At iFlytek's Global 1024 Developer Festival this afternoon, iFlytek announced the debut of SparkAudio 1.0, the first Spark speech foundation model.
SparkAudio 1.0 integrates capabilities such as machine translation, speech recognition, and semantic understanding, significantly enhancing foundational speech capabilities.
The model is claimed to "perform excellently" in real-time speaker separation, environmental understanding, audio understanding, and emotion recognition, advancing artificial intelligence toward applications in the physical world.
Through an analysis of a movie clip, the company demonstrated the model's precise recognition of sound content, background, and speaker gender, as well as the accuracy of its scene judgments.
SparkAudio 1.0 is now fully available in iFlytek Input Method 16.0, iFlytek Hearing, iFlytek Office Notebook, and iFlytek Translator, supporting seamless Chinese-English switching and real-time speaker recognition.
IT Home noted that iFlytek also released a hardware device called the "iFlytek AI Recording Ring," equipped with a 4 + 1 ring microphone array and Wi-Fi 6 transmission, claimed to achieve an overall recognition accuracy of over 96%, transcribing 2 hours of recording in just 2 minutes.