The listed models are MAI-Voice-2.1 and MAI-Voice-2.1-Flash for speech generation, and MAI-Transcribe-2 Streaming for partial transcript updates as audio arrives. The changelog includes AI SDK examples for speech generation and streaming transcription. Vercel says AI Gateway bills the models at listed rates, with no platform fee or inference markup. The announcement establishes availability and describes integration paths; it does not provide independent performance, security, or data-retention results.
Raw SignalOct 1, 20261 min read1 source
We partnered with @MicrosoftAI to bring their secure, transparent, and cost-efficient models to AI Gateway.
In one minute
Vercel says Microsoft AI’s MAI audio models are now available through AI Gateway.