MAI-Voice-2

Microsoft's expressive long-form speech model, ranked first on the design-arena text-to-speech leaderboard.

POST/v1/media/queue

$0.0465/1K chars

Overview

MAI-Voice-2 is Microsoft's expressive text-to-speech model, built for conversational assistants, media narration, accessibility, and education. It generates 24 kHz mono speech across 15 languages and 18 locales with fine-grained control over tone and delivery, and currently ranks first on the design-arena text-to-speech leaderboard.

Property	Value
Model ID	`microsoft/mai-voice-2`
Alias	`mai-voice`
Upstream Model	`microsoft/mai-voice-2`
Category	Text to Speech
Languages	15 languages across 18 locales
Output	`mp3` (default) or `pcm`
Pricing	$0.0465 per 1,000 characters

Usage

All media models use the async job queue. Submit a job, then poll for the result.

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: 'Your text to speak goes here.',
    options: { voice: 'en-US-Harper:MAI-Voice-2' },
  }),
});
const { data } = await res.json();
// data.jobId — use this to poll for results

curl -X POST https://api.yepapi.com/v1/media/queue \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "microsoft/mai-voice-2", "prompt": "Your text to speak goes here."}'

Step 2: Poll for Result

const status = await fetch(`https://api.yepapi.com/v1/media/status/${data.jobId}`, {
  headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status — "pending" | "processing" | "completed" | "failed"
// job.result.audio — { mimeType, base64 } when completed

curl https://api.yepapi.com/v1/media/status/JOB_ID \
  -H "x-api-key: YOUR_API_KEY"

Write the audio to a file:

import { writeFileSync } from 'node:fs';

writeFileSync('speech.mp3', Buffer.from(job.result.audio.base64, 'base64'));

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	`microsoft/mai-voice-2`	—
`prompt`	`string`	Yes	The text to speak (max 50,000 bytes)	—
`options.voice`	`string`	No	Voice identifier	`en-US-Harper:MAI-Voice-2`
`options.outputFormat`	`string`	No	`mp3` (default) or `pcm`	`mp3`
`options.speed`	`number`	No	Playback speed multiplier. Honoured only by models that support it	`1.0`

Voices

en-US-Harper:MAI-Voice-2 is used when options.voice is omitted. 4 voices available:

en-US-Harper:MAI-Voice-2
es-MX-Valeria:MAI-Voice-2
fr-FR-Soleil:MAI-Voice-2
de-DE-Klaus:MAI-Voice-2

Features

Ranked #1 on the design-arena text-to-speech leaderboard
15 languages across 18 locales
Expressive tone and delivery control
Built for long-form narration and conversational agents

Billing

Speech is billed on the length of the input text, in UTF-8 bytes — for English text one byte is one character. The cost is known before synthesis starts, so the balance check at submit time quotes the exact final charge. Jobs have a $0.01 minimum.

Under the Hood

MAI-Voice-2

On this page