Trending storyDeveloping
Microsoft ships transcription and speech synthesis models for voice agents
1 report1 sourceupdated 1 hour ago
What happened
AI digest
The Decoder reported on October 2, 2026 that Microsoft AI released real-time transcription and speech synthesis models built for voice agents. The release covers MAI-Transcribe-2-Streaming plus two speech synthesis models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash. The report gives no performance figures, availability, pricing or use cases.
Written by AI from the coverage · updated 52 minutes ago
Coverage
Follow the reports to see the story from different sides.
Oct 2
- The DecoderMicrosoft AI releases new transcription and text-to-speech models for voice agents
Microsoft AI 发布实时转录模型 MAI-Transcribe-2-Streaming，以及语音合成模型 MAI-Voice-2.1 和 MAI-Voice-2.1-Flash。
Heat over time
Not enough continuous observations to draw a trend yet.