MAI-Voice-2 API Benchmarks, Pricing & Provider Data

Text-To-Speech

MAI-Voice-2 is a high-fidelity, expressive text-to-speech model from Microsoft, powered by Azure AI Speech. It synthesizes natural-sounding speech across 10+ languages with support for expressive SSML...

Specifications

Technical Details

Input
Output
Released: Jun 2026
Documentation

Tokenizer

Other

Architecture

text->speech

Moderated

No

Supported parameters

max_completion_tokensmax_tokenstemperaturetop_p

Supported voices

en-US-Harper:MAI-Voice-2es-MX-Valeria:MAI-Voice-2fr-FR-Soleil:MAI-Voice-2de-DE-Klaus:MAI-Voice-2

Data as of Jul 29, 2026, 09:53 AMRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Standard benchmark data may include BenchLM and other public sources.