opendunes

MAI-Voice-2.1

by MicrosoftReleased 1 October 2026

MAI-Voice-2.1 turns text into speech in 23 languages and returns audio from about 97 named voices. It is Microsoft's most expressive voice model, with detailed rhythm and emotion and a speaker who stays the same across a long recording. Use it for audiobooks, podcasts, lectures and brand audio where polish matters more than speed.

TakesText
GivesAudio
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 4,39 DA per paragraph read aloud3 000 DA buys about 680 paragraphs read aloud

One paragraph read aloud, the ordinary use

600 characters sent× 7 322,38 DA per 1M4,39 DA
Total≈ 4,39 DA

Every rate

Meter↑ you send↓ comes back
Characters7 322,38 DA

per 1M characters

A 250-character brand announcement voiced≈ 1,83 DA
A 1,500-character podcast intro and ad read≈ 10,98 DA
A 4,000-character explainer video voice-over≈ 29,29 DA
A 12,000-character audiobook chapter narrated≈ 87,87 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M characters: ↑ what you send.

Azure…
↑
7 322,38
Latency
…
Provider↑ SentLatencyUptime
Azure7 322,38……

You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/audio/speech
Base URL
https://opendunes.com/v1
Model ID
microsoft/mai-voice-2.1
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

with client.audio.speech.with_streaming_response.create(
    model="microsoft/mai-voice-2.1",
    input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
    voice="cs-CZ-Grant:MAI-Voice-2.1",
) as resp:
    resp.stream_to_file("speech.mp3")
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Questions about MAI-Voice-2.1

  • How much does MAI-Voice-2.1 cost in dinars?

    About 4,39 DA per paragraph read aloud. ↑ 7 322,38 DA per 1M characters.

  • Is MAI-Voice-2.1 free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is MAI-Voice-2.1 best for?

    MAI-Voice-2.1 turns text into speech in 23 languages and returns audio from about 97 named voices. It is Microsoft's most expressive voice model, with detailed rhythm and emotion and a speaker who stays the same across a long recording. Use it for audiobooks, podcasts, lectures and brand audio where polish matters more than speed.

  • MAI-Voice-2.1 or MAI-Voice-2.1-Flash?

    MAI-Voice-2.1-Flash costs 1,39 DA less for the same paragraph read aloud.

  • How do I pay for MAI-Voice-2.1 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, MAI-Voice-2.1 included, is paid from that balance. No foreign card, no conversion.

  • Does MAI-Voice-2.1 work in Arabic, French or Darja?

    Microsoft names no languages for MAI-Voice-2.1. Arabic, French and Darja: not stated.

  • How many voices, and can it clone mine?

    97 voices. Cloning from a sample: not stated.

  • Who makes MAI-Voice-2.1, and when was it released?

    Microsoft. Released 1 October 2026.

Other Microsoft models, priced in dinars

See all Microsoft models
Microsoft-Decision-1Microsoft · Oct 9, 2026

Microsoft-Decision-1 reads the content you send and returns a probability for each of a fixed set of answer options instead of writing text. Use it where a pick-one call drives your app: sorting tickets, routing requests, checking an answer, or deciding whether to act, wait or flag the case for a person. It reads about 33 pages at once. It cannot chat, translate or summarize, so pair it with a text model for those jobs.

32 pages per call
≈0,014 DAper case
View model
MAI-Voice-2.1-FlashMicrosoft · Oct 1, 2026

The low-latency text-to-speech from Microsoft AI for real-time voice, producing expressive speech in 23 languages for voice agents, assistants and call centres, where the full MAI-Voice-2.1 gives up speed for fidelity

97 voices
≈3,00 DAper paragraph read aloud
View model
MAI-Voice-2Microsoft · Jun 2, 2026

#1 for realistic voice · MAI-Voice-2 turns text into speech and returns audio, with control over tone and delivery and a way to give different lines to different speakers. It covers 15 languages in 18 regional versions and offers four ready voices: US English, Mexican Spanish, French and German. Choose it for narration, tutorials and assistants where natural delivery counts more than speed.

4 voices
≈4,39 DAper paragraph read aloud
View model
MAI-Transcribe 1.5Microsoft · Jun 2, 2026

Microsoft AI's speech recognition for captions, call records, subtitles and accessibility, reliable across 43 languages, many accents and noisy real-world audio, faster than version 1 on long files but without speaker labels

2,00 DAper minute of audio
View model