Alibaba
Fun-ASR
Fun-ASR is an automatic speech recognition model for transcribing recorded audio into text. This ID denotes the November 7, 2025 snapshot. Alibaba’s release listing places its international launch on…
Explore modelEnglish
MODEL DIRECTORY
New releases, in one place. Explore models by their publication date.
Fun-ASR is an automatic speech recognition model for transcribing recorded audio into text. This ID denotes the November 7, 2025 snapshot. Alibaba’s release listing places its international launch on…
Fun-ASR-Realtime is an end-to-end, real-time automatic speech recognition model from Tongyi Lab. It takes speech audio as input and produces text, with contextual awareness and noise robustness.…