Microsoft: MAI Transcribe 2
One API key. Live prices. Ready-to-run code.
MAI-Transcribe-2 is Microsoft's high-accuracy multilingual speech-to-text model designed for fast, production-scale transcription across 60 languages and challenging real-world audio conditions.
Served by OneInfer. Use it with the same API key and pay-as-you-go wallet as every other model in the catalog.
microsoft/MAI-Transcribe-2Call MAI Transcribe 2 in 4 steps
Create a key in the Console. The same key works for every model on OneInfer.
- Context
- N/A
- Input
- audio
- Output
- text
- Tool calling
- Not listed
About this model
MAI-Transcribe-2 is Microsoft's high-accuracy multilingual speech-to-text model designed for fast, production-scale transcription across 60 languages and challenging real-world audio conditions. It provides automatic language identification, speaker diarization, word-level and segment-level timestamps, keyword biasing for domain-specific terminology, code-switching support, and configurable clean or verbatim transcription styles. The model is optimized for meetings, call-center conversations, clinical notes, legal documentation, captions, accessibility, media transcription, content workflows, and voice-agent applications. It combines high transcription accuracy with extremely high batch throughput, processing approximately one hour of audio in around 10 seconds under Microsoft's benchmark conditions.
Input modalities
audio
Accepted as model input
Providers
Available routing options for this model through OneInfer.
- Available
- Speech transcription
- $0.100 / hour
- Routing
- OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Speech transcriptionSTT | $0.100 / hour |
Performance and benchmarks
Independent evaluations and live cluster operational metrics
We haven’t measured this model yet. Published academic results are under Academic evaluations.
API guide
Generate your access token
Use your API key to generate the JWT access token required by the Models API.
Add the JWT token
Copy the generated JWT token and replace
JWT_TOKENin the example below.Check your credits
If your balance is too low, before calling the model.
Run the API example
Choose your preferred language, copy the example, and send your first model request.
curl -X POST https://api.oneinfer.ai/v1/ula/transcribe \ -H "Authorization: Bearer YOUR_JWT_TOKEN" \ -F "file=@audio.mp3" \ -F 'transcription_request_json={"model":"microsoft/MAI-Transcribe-2","language":"en"}'
Community reviews and ratings
Visitor and developer evaluations of Microsoft: MAI Transcribe 2's real-world intelligence, code accuracy, and speed
Top community tags
No community reviews yet
Be the first to share developer feedback on Microsoft: MAI Transcribe 2's latency, code accuracy, and reliability in production.