Skip to content

Microsoft MAI-Voice-2.1-Flash Microsoft · text-to-speech (TTS) API

289 ms median time to first audio on Cekura (read October 27, 2026); not measured by Coval, so no speed tier.

Benchmark summary: No speed tier: Coval, the source of the tiers, does not measure this model.

Microsoft MAI-Voice-2.1-Flash is a text-to-speech (TTS) API from Microsoft, measured by one independent benchmark, Cekura.

Visit website
Cekura Microsoft

Speed tier

Not measured by Coval

No speed tier: Coval, the source of the tiers, does not measure this model.

Median time to first audioCoval, 30 days
—
P95 time to first audio (slow turns)Coval, 30 days
—
Naturalness EloSpeko
not rated
Listener Elo (95% interval)Artificial Analysis
not rated
Numbers and dates (0 to 1)Speko
not rated
List price per 1M charactersall sources
not published

Figures as of October 27, 2026. No combined score: methodology

Gradium TTS vs Microsoft MAI-Voice-2.1-Flash Fastest TTS APIs, by speed tier

Speed

Cekura measures 289 ms (median) from sending a full sentence to the first sound (12th lowest of the 26 models Cekura measures); it does not report a figure with text streamed word by word.

Voice quality

Speko, Artificial Analysis and Cekura do not rate its voice quality.

Accuracy

Cekura's transcribers score 79% on numbers and shorthand and 67% on codes and addresses.

Price

No list price is published by Coval, Speko, Artificial Analysis or Cekura for this model.

Benchmark measurements

Streaming

Streaming
Measured

Cekura

Time to first audio, full sentence sent at once (median)
289 ms
Numbers and shorthand
79%
Codes and addresses
67%
Read from context
75%
Medical terms
92%
Cekura benchmark
benchmarks.cekura.ai

Not collected

Similar TTS models