MAI-Transcribe 2 · vercel
MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech, speaker diarization, word-level timestamps, keyword biasing for domain-specific terminology, and configurable verbatim or clean transcription styles. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, and is faster than MAI-Transcribe-1.5 on long-form audio.
Precio, $ $0.001667 / minuto
Alertas de precio
API
API compatible con OpenAI: los SDK oficiales de OpenAI funcionan con esta URL base. Sustituye YOUR_API_KEY por tu clave del proveedor.
| URL base de la API | |
|---|---|
| Endpoint | |
| ID del modelo | |
curl
curl https://ai-gateway.vercel.sh/v1/audio/transcriptions \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "model=microsoft/mai-transcribe-2" -F "file=@audio.mp3"Python
import requests
r = requests.post(
"https://ai-gateway.vercel.sh/v1/audio/transcriptions",
headers={"Authorization": "Bearer YOUR_API_KEY"},
data={"model": "microsoft/mai-transcribe-2"},
files={"file": open("audio.mp3", "rb")},
)
print(r.json())JavaScript
const form = new FormData();
form.append("model", "microsoft/mai-transcribe-2");
form.append("file", fileInput.files[0]);
const r = await fetch("https://ai-gateway.vercel.sh/v1/audio/transcriptions", {
method: "POST",
headers: {Authorization: "Bearer YOUR_API_KEY"},
body: form,
});
console.log(await r.json());Solicitud (JSON)
{
"model": "microsoft/mai-transcribe-2",
"file": "@audio.mp3"
}Respuesta (JSON)
{
"text": "Hello!"
}La dirección se toma de la lista de modelos del proveedor; compruébala con su documentación.
Source: AI Rate Card, https://airatecard.com/es/c/offer%3Avercel%7Cmicrosoft/mai-transcribe-2, prices checked 2026-11-04; seller's page: https://vercel.com/ai-gateway/models/mai-transcribe-2
Datos técnicos
ID: offer:vercel|microsoft/mai-transcribe-2