MAI-Voice-2.1-Flash · vercel
MAI-Voice-2.1-Flash is a text-to-speech model built for fast, low-latency generation. It produces high- fidelity, natural, and expressive speech across 23 languages and supports gated instant voice cloning, all while being optimized for real-time responsiveness. Its human-like intonation, rhythm, and emotional nuance make it ideal for voice agents, assistants, and other interactive scenarios where latency and cost are critical.
Price, $ $15.00 / 1M chars
Price alerts
API
OpenAI-compatible API: the official OpenAI SDKs work with this base URL. Replace YOUR_API_KEY with your key from the provider.
| API base URL | |
|---|---|
| Endpoint | |
| Model id | |
curl
curl https://ai-gateway.vercel.sh/v1/audio/speech \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "microsoft/mai-voice-2.1-flash", "input": "Hello!", "voice": "alloy"}'Python
import requests
r = requests.post(
"https://ai-gateway.vercel.sh/v1/audio/speech",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "microsoft/mai-voice-2.1-flash",
"input": "Hello!",
"voice": "alloy"
},
)
print(r.json())JavaScript
const r = await fetch("https://ai-gateway.vercel.sh/v1/audio/speech", {
method: "POST",
headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
body: JSON.stringify({
"model": "microsoft/mai-voice-2.1-flash",
"input": "Hello!",
"voice": "alloy"
}),
});
console.log(await r.blob());Request (JSON)
{
"model": "microsoft/mai-voice-2.1-flash",
"input": "Hello!",
"voice": "alloy"
}Response (JSON)
audio bytes (audio/mpeg)The address is taken from the provider's model list; check it against the provider's documentation.
Source: AI Rate Card, https://airatecard.com/en/c/offer%3Avercel%7Cmicrosoft/mai-voice-2.1-flash, prices checked 2026-11-04; seller's page: https://vercel.com/ai-gateway/models/mai-voice-2.1-flash
Technical details
ID: offer:vercel|microsoft/mai-voice-2.1-flash