Microsoft AI has released a prototype demo that links three of its in-house models — for speech recognition, transcription and coding — to turn spoken instructions into working code. Built on a fork of VS Code, the demo shows a workflow in which MAI-Transcribe transcribes a user's voice instructions, MAI-Code-1-Flash generates code, and MAI-Voice returns spoken feedback. The roughly 71-second clip was also published on YouTube as the Voice Coding Demo.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.