MAI-Transcribe 2

microsoft/mai-transcribe-2

A speech-to-text model, at $0.001764 per minute.

Details

Maker: microsoft
Kind: Transcription
Price: $0.001764 per minute
Capabilities: None listed
Takes: Audio
Returns: Text
Zero data retention: Yes, on every provider
No training on requests: Yes, on every provider
Released: 2026-09-03

Description

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.

Call it

curl

curl https://phantom.codes/v1/audio/transcriptions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -F file=@audio.mp3 \
  -F model=microsoft/mai-transcribe-2

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model