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.
| Billing | Price |
|---|---|
| Rate | $0.0465/1K chars |
| What it costs | Per 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
$0.01
Per call
Yep, that's it.
Playground coming soon — use the API endpoint directly with your API key.
MAI-Voice-2 specs
| Provider | Microsoft |
|---|---|
| Model ID | microsoft/mai-voice-2 |
| Endpoint | /v1/media/queue |
| Type | Text to Speech |
| Output formats | mp3 |
| Voices | 4 presets (default en-US-Harper:MAI-Voice-2) |
How to get a MAI-Voice-2 API key
- 1
Create an account
Sign up at yepapi.com with Google or email. It takes about 30 seconds.
- 2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
- 3
Call MAI-Voice-2
Send a request to /v1/media/queue with the x-api-key header and model "microsoft/mai-voice-2".
- 4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.
Strengths
MAI-Voice-2 tops the design-arena text-to-speech leaderboard, and takes first place for audio realism as well.
One model covers English, Spanish, French, German and eleven more languages without switching providers.
Fine-grained control over tone and pacing makes it suitable for narration and character work, not just flat readouts.
Built for audiobooks, courseware, and accessibility playback where hours of audio have to stay consistent.
Quick start
Copy this snippet and start making calls with MAI-Voice-2.
// Step 1: Submit job
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "microsoft/mai-voice-2",
"prompt": "Welcome back. Your report finished processing overnight, and there are three items that need your attention this morning.",
"options": {
"voice": "en-US-Harper:MAI-Voice-2"
}
}),
});
const { data } = await res.json();
const jobId = data.jobId;
// Step 2: Poll for result
const status = await fetch(`https://api.yepapi.com/v1/media/status/${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.
| Model | Provider | Price |
|---|---|---|
| MAI-Voice-2 | Microsoft | $0.0465/1K chars |
| MAI-Voice-2.1 Flash | Microsoft | $0.0316/1K chars |
| MAI-Voice-2 Flash | Microsoft | $0.0317/1K chars |
| MAI-Voice-2.1 | Microsoft | $0.0464/1K chars |
| Kokoro 82M | hexgrad | $0.0014/1K chars |
| Fish Audio Drama 3 | Fish Audio | $0.0042/1K chars |
| HeyGen Voice Turbo | HeyGen | $0.0084/1K chars |
| Sesame CSM 1B | Sesame | $0.0148/1K chars |
Why use MAI-Voice-2 through YepAPI?
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.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
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.
Explore more models
MAI-Voice-2.1 Flash
MicrosoftMAI-Voice-2.1 Flash text to speech — low-latency expressive speech in 23 languages, billed on input length.
MAI-Voice-2 Flash
MicrosoftMAI-Voice-2 Flash text to speech — low-latency speech for voice agents, billed on input length.
MAI-Voice-2.1
MicrosoftMAI-Voice-2.1 text to speech — studio-grade speech in 23 languages, billed on input length.
MiniMax Speech 2.8 Turbo
MiniMaxMiniMax Speech 2.8 Turbo text to speech — fast, flexible-voice speech, billed on input length.
Eleven v4
ElevenLabsEleven v4 text to speech — ElevenLabs' most expressive model, 90+ languages, billed on input length.
Eleven Flash v2
ElevenLabsEleven Flash v2 text to speech — ultra-low-latency English speech, billed on input length.
More Text to Speech models
- Fish Audio S2 Pro API · Fish Audio
- Qwen-Audio 3.0 TTS Plus API · Qwen
- Eleven v3 API · ElevenLabs
- Grok Voice TTS 1.0 API · xAI
- Seed Audio 1.0 API · ByteDance
- Eleven Flash v2.5 API · ElevenLabs
- Eleven Turbo v2 API · ElevenLabs
- MiniMax Speech 2.8 HD API · MiniMax
- Deepgram Flux TTS API · Deepgram
- Voxtral Mini TTS API · Mistral
- Fish Audio S2.1 Pro API · Fish Audio
- Voxtral TTS 3 API · Mistral