YepAPI
MicrosoftText to Speech/v1/media/queue

MAI-Voice-2 API

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

Microsoft's expressive text-to-speech model and the current #1 on the design-arena TTS leaderboard. 15 languages across 18 locales, 24 kHz mono output, tuned for long-form narration and conversational agents.

Takes 30 seconds.

MAI-Voice-2 API pricing

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

BillingPrice
Rate$0.0465/1K chars
What it costsPer job
Short reply200 characters$0.0093
Blog post narration10,000 characters (~1,600 words)$0.465
Audiobook chapter100,000 characters$4.65

4,900+

Developers

2.3M+

API calls served

184

Endpoints

$0.01

Per call

Yep, that's it.

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

MAI-Voice-2 specs

ProviderMicrosoft
Model IDmicrosoft/mai-voice-2
Endpoint/v1/media/queue
TypeText to Speech
Output formatsmp3
Voices4 presets (default en-US-Harper:MAI-Voice-2)

How to get a MAI-Voice-2 API key

  1. 1

    Create an account

    Sign up at yepapi.com with Google or email. It takes about 30 seconds.

  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

    Send a request to /v1/media/queue with the x-api-key header and model "microsoft/mai-voice-2".

  4. 4

    Pay as you go

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

Strengths

✓
Ranked #1 for speech

MAI-Voice-2 tops the design-arena text-to-speech leaderboard, and takes first place for audio realism as well.

✓
15 languages, 18 locales

One model covers English, Spanish, French, German and eleven more languages without switching providers.

✓
Expressive delivery

Fine-grained control over tone and pacing makes it suitable for narration and character work, not just flat readouts.

✓
Long-form ready

Built for audiobooks, courseware, and accessibility playback where hours of audio have to stay consistent.

Quick start

Copy this snippet and start making calls with MAI-Voice-2.

// 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",
    "prompt": "Welcome back. Your report finished processing overnight, and there are three items that need your attention this morning.",
    "options": {
      "voice": "en-US-Harper:MAI-Voice-2"
    }
  }),
});
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 vs similar models

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

ModelProviderPrice
MAI-Voice-2Microsoft$0.0465/1K chars
MAI-Voice-2.1 FlashMicrosoft$0.0316/1K chars
MAI-Voice-2 FlashMicrosoft$0.0317/1K chars
MAI-Voice-2.1Microsoft$0.0464/1K 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 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 API — the top-ranked text-to-speech model

MAI-Voice-2 is Microsoft's expressive text-to-speech model, currently ranked first on the design-arena leaderboard for both text-to-speech and audio realism. It generates 24 kHz mono speech across 15 languages and 18 locales with fine-grained control over tone and delivery.

Through YepAPI you submit text to `/v1/media/queue`, poll the job, and download the audio — one key, billed on input length at $0.0465 per 1,000 characters, with no separate speech contract to sign.

Start generating in 30 seconds

Pay per call, no subscriptions.

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's expressive text-to-speech model and the current #1 on the design-arena TTS leaderboard. 15 languages across 18 locales, 24 kHz mono output, tuned for long-form narration and conversational agents.

MAI-Voice-2 costs $0.0465/1K 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 and every other model — no separate Microsoft account or waitlist.

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

Ready to use MAI-Voice-2?

Pay per call, no subscriptions.

Explore more models