Microsoft MAI-Transcribe-2
Use Microsoft MAI-Transcribe-2 through Speechall’s unified speech-to-text API. Rates represent USD credit usage; review purchase fees in your billing quote. Check the features and limits below before switching models.
Microsoft AI MAI-Transcribe-2 for multilingual batch speech-to-text using Azure Speech enhanced mode. Supports 60 languages, automatic language identification, speaker diarization, word-level timestamps, keyword biasing, and verbatim or clean output. Public preview; no production SLA.
Model ID
microsoft.mai-transcribe-2
Use this ID when making API calls to reference this model
Provider
Azure
Model Type
general
Accuracy Tier
premium
Release Date
September 3, 2026
Supported Languages
File transcription credit usage
$0.10000/audio hour
$0.00003/audio second
Maximum Duration
2h 0m
Maximum File Size
238.42 MB
Supported capabilities and functionalities
Core Features
Subtitle Formats
Input/output formats and technical details
Subtitle Format Support
Supported Audio Encodings
From model comparison to your first transcript
- Create a Speechall account and create an API key in the console.
- Review your credit balance and purchase quote. Usage draws down prepaid credits; checkout shows purchase fees and conversion.
- Test models with your own audio in the playground, then follow the API quickstart.