MAI-Voice-2.1-Flash
Low-latency MAI-Voice for real-time, high-volume speech.
MAI-Voice-2.1-Flash is the high-volume, latency-sensitive variant of MAI-Voice-2.1, with the same 23 languages. Microsoft reports 150 ms end-to-end latency for up to 45 seconds of audio (vendor-reported).
- Provider
- Microsoft AI
- Type
- Text-to-speech
- Released
- Oct 1, 2026
- Input
- text
- Output
- audio
- Open weights
- No
Best for
- Real-time / low latency
- High volume / low cost
- Agents
Strengths
- ≈150 ms latency (vendor-reported)
- 23 languages
More from Microsoft AI
- Microsoft-Decision-1 — Microsoft AI. Microsoft’s small decision-scoring model: calibrated probabilities over fixed options.
- MAI-Image-2.6 — Microsoft AI. Microsoft AI’s in-house image model.
- MAI-Image-2.7 Preview — Microsoft AI. Preview of Microsoft AI’s next image model, editing only for now.
- MAI-Voice-2.1 — Microsoft AI. Microsoft AI’s most expressive multilingual text-to-speech model.
- MAI-Transcribe-2 — Microsoft AI. Microsoft AI’s in-house speech-to-text model.
- MAI-Transcribe-2-Streaming — Microsoft AI. Microsoft AI’s first streaming speech-to-text model, in 60 languages.