MAI Voice 2.1 Flash is Microsoft's language model, starting at $15.00 / 1M input. A low-latency text-to-speech model producing high-fidelity, expressive speech across 23 languages with support for gated instant voice cloning.
Specifications
Canonical IDmicrosoft-mai-2-1-flash-voice
TypeLanguage
StatusActive
CreatorMicrosoftMicrosoft
Providers
Input ModalitiesText
Output ModalitiesText
Release Date · 12 days ago

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Vercel AI Gateway logo
Vercel AI Gateway
microsoft/mai-voice-2.1-flash
$15.00

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MAI Voice 2.1 Flash—$15.00—Current
MAI Voice 2 Flash—$15.00—Available
MAI Image 2.6 Flash—32K$1.75—Available
MAI Code 1 Flash—128K——Available
MAI Code 1 Flash Internal—128K——Available
MAI Code 1.1 Flash—128K——Available
MAI Cyber 1 Flash—256K$0.600$3.50Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
MAI Transcribe 2 Streaming————
MAI Voice 2.1——$22.00—
MAI Transcribe 2————
MAI Voice 2——$22.00—
MAI Image 2 Efficient—————
MAI Image 2.5——32K$5.00—
MAI Image 2.6——32K$5.00—
MAI Image 2.6 Preview—————
MAI Image 2.5 ProPro—32K$5.00—
MAI Transcribe 1.5————

Model IDs

microsoft-mai-2-1-flash-voice
microsoft/mai-voice-2.1-flash