Start creating

MAI-Voice-2.1AI text to speech

Microsoft's most natural voices, for narration, across 23 languages. On Leap, it sits beside 174 other models in one studio.

  • Text to speech

Your words wait while you sign in.

  • No subscription
  • Every top model, one account
  • Pay per run, priced before it starts

Listen / Iris

0 / 8 s
Read the transcript

Hi, I'm testing Leap's voices. Can you hear the difference between each one? Let's find out together.

Listen / Documentary: the high desert at night

0 / 10 s
Read the transcript

In the high desert, the night drops forty degrees in an hour. The stones that baked all day begin to crack, and the whole valley ticks like a clock.

AI text to speech

MAI-Voice-2.1 at a glance

MAI-Voice-2.1 is a text-to-speech model from Microsoft. It makes speech from your text.

Made by
Microsoft
Makes
Speech
Starts from
Your text
Voices
3 to choose from
Text
Up to 4,000 characters
Price
$0.0297 per 1,000 characters
Updated
October 2, 2026
  1. 01Write the words, pick a voice
  2. 02See the exact price, then press go
  3. 03Keep it in your library, or take it further

Pick the right one

MAI-Voice-2.1 and its siblings

ModelBest forPrice per run
MAI-Voice-2.1 (this page)Microsoft's most natural voices, for narration, across 23 languages.$0.0297 per 1,000 characters
MAI-Voice-2.1 FlashThe fast MAI voice, at a lower price.$0.02025 per 1,000 characters

Start with an idea

Three ways to try MAI-Voice-2.1

Why Leap

Why creators make it on Leap

  1. 01

    Every top model, side by side

    175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.

    See the models
  2. 02

    One click, or full control

    Character Studio, effects and recipes write the prompt for you. Or write your own for any model.

    See the tools
  3. 03

    Your work stays yours

    Everything you make stays in your library while your account is active, and you own what you make here.

    See what people make
  4. 04

    One balance for everything

    The studio, the API and your agents spend the same balance, and every run shows its price before it starts.

    How pricing works

Questions

MAI-Voice-2.1, answered

What is MAI-Voice-2.1?
MAI-Voice-2.1 is a text-to-speech model from Microsoft. Microsoft's most natural voices, for narration, across 23 languages. On Leap it runs in one studio beside every other top model, with one account.
Which voices can I use?
3 voices, among them Jasper, Grant and Iris. You can hear each one in the studio before you run it.
How much text can it read in one run?
Up to 4,000 characters. You pay for the characters you send, with the price shown before you press go.
How is it different from MAI-Voice-2.1 Flash?
MAI-Voice-2.1: Microsoft's most natural voices, for narration, across 23 languages. MAI-Voice-2.1 Flash: The fast MAI voice, at a lower price. They all run in the same studio, so you can try one prompt on each.
How much does a run cost?
It costs $0.0297 per 1,000 characters. You see the exact price before you press go, and a run that fails costs nothing.
Is MAI-Voice-2.1 free to try?
No. There is no free credit: you add credit from $5, and your first top-up has no card fee. It costs $0.0297 per 1,000 characters. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?
Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?
Yes. Leap's REST API runs it as microsoft/mai-voice-2.1, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need a Microsoft account?
No. Leap sends your request to Microsoft's model and gives you what it makes. One Leap account runs MAI-Voice-2.1 and every other model, in the studio, through the API and from your agents.

Your idea, MAI-Voice-2.1.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with MAI-Voice-2.1

For developers

Run MAI-Voice-2.1 from code

Model ID
microsoft/mai-voice-2.1
Makes
Voice and sound
Pricing
Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Texttext
Text, up to 4,000 characters, required
Voicevoice
Jasper, Grant, Iris. Default: Jasper

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "microsoft/mai-voice-2.1",    "input": {      "text": "Hi, I'\''m testing Leap'\''s voices. Can you hear the difference between each one? Let'\''s find out together."    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"