Voice and music · by Microsoft

Azure Speech

Transcribe audio, with recognition trained on your own vocabulary.

speech, link → text, data · speech, text → data
Way in
Official APISign up yourself, api key
To start
$F0: 5 hrs/month standard realtime
Runs
In the cloudAlso through Azure
Checked
Nov 3, 2026Prices as of that day

What it can do 2

Transcribe audio (realtime, fast or batch) with diarization and language IDF0: 5 audio hrs/month realtime; no batch on F0speech, link → text, data~$1.67/1k min for MAI-Transcribe-2 (AA listing; Azure page shows placeholders, promo until 2026-12-31)
Train and host custom speech modelsspeech, text → dataper compute hour + hosting (rates not visible)

Does the same job

Prices and limits as of Nov 3, 2026, from Microsoft’s own pages. They change; check before you rely on them.Not affiliated with Microsoft. Not advice.Rankings: Artificial Analysis.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.