模型发布VIDEO
Microsoft releases three new speech and transcription models
MAI-Transcribe-2-Streaming focuses on streaming transcription, while MAI-Voice-2.1 and its Flash version improve speech naturalness and cut waiting time between turns.
Microsoft AI
@MicrosoftAIArchived 2026.10.02Originally posted 2026.10.02
Microsoft AI @MicrosoftAIOriginally posted 2026.10.02
Introducing 3 new models: MAI-Transcribe-2-Streaming, MAI-Voice-2.1 and MAI-Voice-2.1-Flash. Accurate streaming transcription. Natural speech and less waiting between turns. Build voice agents that keep the conversation moving!
x.com/microsoftai/status/2105693024013467905Archived 2026.10.02 10:32