YepAPI
MicrosoftText to Speech/v1/media/queue

MAI-Voice-2.1 API

MAI-Voice-2.1 text to speech — studio-grade speech in 23 languages, billed on input length.

Microsoft AI's highest-fidelity, most expressive text-to-speech model. Studio-grade speech across 23 languages and 97 voices, with detailed prosody and speaker consistency over long-form content.

Full Docs Get API Key — Free $5 Credit

No credit card required. Takes 30 seconds.

MAI-Voice-2.1 API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated October 23, 2026.

BillingPrice
Rate$0.0464/1K chars
What it costsPer job
Short reply200 characters$0.0093
Blog post narration10,000 characters (~1,600 words)$0.464
Audiobook chapter100,000 characters$4.64

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Playground coming soon — use the API endpoint directly with your API key.

MAI-Voice-2.1 specs

ProviderMicrosoft
Model IDmicrosoft/mai-voice-2.1
Endpoint/v1/media/queue
TypeText to Speech
Output formatsmp3
Voices12 presets (default en-US-Harper:MAI-Voice-2.1)

How to get a MAI-Voice-2.1 API key

  1. 1

    Create a free account

    Sign up at yepapi.com with Google or email. It takes about 30 seconds and needs no card.

  2. 2

    Create an API key

    Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.

  3. 3

    Call MAI-Voice-2.1

    Send a request to /v1/media/queue with the x-api-key header and model "microsoft/mai-voice-2.1".

  4. 4

    Pay as you go

    Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓
Highest-fidelity MAI voice

Microsoft AI's highest-fidelity, most expressive text-to-speech model, producing natural, studio-grade speech.

✓
23 languages, 97 voices

Voices across 28 locales, from US and UK English to Hindi, Korean, Portuguese, and Mandarin.

✓
Detailed prosody

Nuanced expressiveness and prosody for reads that carry meaning, not just words.

✓
Long-form consistency

Speaker consistency holds over long-form content such as audiobooks and courseware.

Quick start

Copy this snippet and start making calls with MAI-Voice-2.1.

// Step 1: Submit job
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "microsoft/mai-voice-2.1",
    "prompt": "Welcome to module four. Over the next twenty minutes we'll walk through how the pieces fit together, one step at a time.",
    "options": {
      "voice": "en-US-Harper:MAI-Voice-2.1"
    }
  }),
});
const { data } = await res.json();
const jobId = data.jobId;

// Step 2: Poll for result
const status = await fetch(`https://api.yepapi.com/v1/media/status/${jobId}`, {
  headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status: "pending" | "processing" | "completed" | "failed"
// job.result: { text?, image?, audio?, video? }

MAI-Voice-2.1 vs similar models

Every model below runs on the same API key — switch by changing the model ID.

ModelProviderPrice
MAI-Voice-2.1Microsoft$0.0464/1K chars
MAI-Voice-2.1 FlashMicrosoft$0.0316/1K chars
MAI-Voice-2 FlashMicrosoft$0.0317/1K chars
MAI-Voice-2Microsoft$0.0465/1K chars
Kokoro 82Mhexgrad$0.0014/1K chars
Fish Audio Drama 3Fish Audio$0.0042/1K chars
HeyGen Voice TurboHeyGen$0.0084/1K chars
Sesame CSM 1BSesame$0.0148/1K chars

Why use MAI-Voice-2.1 through YepAPI?

✓One API key for all models — no separate accounts
✓No monthly minimums — pay per call
✓Switch models with one line of code
✓Simple REST API — works from any language
✓Unified billing across all providers
✓No rate limits for most use cases

MAI-Voice-2.1 API — studio-grade speech from Microsoft AI

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.

Voices are selected by locale-prefixed ID such as `en-US-Harper:MAI-Voice-2.1`. Through YepAPI you submit text to `/v1/media/queue`, poll the job, and download the audio — billed on input length at $0.0464 per 1,000 characters.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”

Marcus T.

SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”

Priya S.

Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”

Jake R.

Indie Hacker

Frequently asked questions

Microsoft AI's highest-fidelity, most expressive text-to-speech model. Studio-grade speech across 23 languages and 97 voices, with detailed prosody and speaker consistency over long-form content.

MAI-Voice-2.1 costs $0.0464/1K chars through YepAPI, billed per request with no monthly fee. For example, a short reply (200 characters) costs about $0.0093.

Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for MAI-Voice-2.1 and every other model — no separate Microsoft account or waitlist.

New YepAPI accounts in most countries get free signup credit, enough to test MAI-Voice-2.1 without a card. After that you pay per request at the rates above — there is no subscription.

Use "microsoft/mai-voice-2.1" as the model on /v1/media/queue. The short alias "mai-voice-2-1" also works.

Ready to use MAI-Voice-2.1?

$5 free credit on signup. No credit card required. Pay per call.

Get API Key — Free $5 Credit Read Docs

Explore more models

MAI-Voice-2 Flash

Microsoft

MAI-Voice-2 Flash text to speech — low-latency speech for voice agents, billed on input length.

Per character

MAI-Voice-2.1 Flash

Microsoft

MAI-Voice-2.1 Flash text to speech — low-latency expressive speech in 23 languages, billed on input length.

Per character

MAI-Voice-2

Microsoft

MAI-Voice-2 text to speech — expressive speech in 15 languages, billed on input length.

Per character

Seed Audio 1.0

ByteDance

Seed Audio 1.0 text to speech — speech and audio from a natural-language prompt, billed on input length.

Per character

Eleven v4 Turbo

ElevenLabs

Eleven v4 Turbo text to speech — Eleven v4's expressive delivery, tuned for speed, billed on input length.

Per character

Fish Audio S2.1 Pro

Fish Audio

Fish Audio S2.1 Pro text to speech — stateless voice cloning, billed on input length.

Per character

More Text to Speech models

All Microsoft models →All AI models →