MAI-Transcribe-1

Production ASR for noisy multilingual audio

API Artificial Intelligence Audio發布於 2026年4月3日

什麼是 MAI-Transcribe-1？

MAI-Transcribe-1 is Microsoft’s new multilingual speech-to-text model built for real-world audio. It delivers best-in-class accuracy across 25 languages, strong robustness in noisy environments, faster batch transcription, and pricing aimed at production speech workflows.

演示

截圖

還沒有評論，來搶沙發吧！