Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $22.00 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About MAI-Voice-1
Microsoft AI voice generation with emotional nuance and speaker identity preservation. Generates 60 seconds of audio in 1 second. Supports custom voice creation from brief audio samples.
Model Specs
Released2026-04-02
ArchitectureTransformer