Skip to content
FluxCDNFluxCDN
esc

Microsoft AI: MAI-Voice-2.1

Text to speech

MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content.

Price
7,929 Toman per 1,000 characters
Endpoint
POST /v1/audio/speech
Published
Oct 1, 2026
Offers
97 voices
Offers
MP3 · WAV
Maker
Microsoft AI

Free plan prices, in Toman at today's rate. Plans and prices

Price on each plan

Per character of the text read, in Toman at today's rate; a text of 1,000 characters is about a minute and a half of speech.

PlanPrice
Free7,929 Toman per 1,000 characters
Pro7,604 Toman per 1,000 characters
Max7,279 Toman per 1,000 characters

Voices

    97 voices in all: any of them may be asked for by name in the API.

    Hear all voices

    Call it

    curl https://ai.fluxcdn.cloud/api/v1/audio/speech -H "Authorization: Bearer $FLUXCDN_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"model": "microsoft/mai-voice-2.1", "input": "سلام! به FluxCDN خوش آمدید.", "voice": "cs-CZ-Grant:MAI-Voice-2.1", "response_format": "mp3"}' \
      --output speech.mp3