From Qianwen to Gaode DingTalk, voice interaction interfaces have been clearly understood by Alibaba.

View Original
CoinNetwork
CryptoWorld News reports that Alibaba's speech large model fun-realtime-asr and fun-realtime-audiochat have topped the rankings on the global authoritative AI evaluation platform Artificial Analysis, surpassing top international models such as GPT-Realtime-2, and achieving first place in three metrics: "Listening Accuracy (Word Error Rate)", "Understanding (Speech Reasoning)", and "Conversational Fluency". As a new human-computer interaction gateway, Alibaba's speech large model family has been deeply integrated into applications such as Qianwen APP, Amap, DingTalk, providing services including real-time speech-to-text, intelligent navigation interaction, and meeting minutes generation.
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned