Skip to content
CallMissed
Book a demo

Explore CallMissed

Back to all models
Speech to Textpreviewmultilingualfile-transcription

MAI-Transcribe-2

by Microsoft · Released Preview

Preview. Microsoft AI's file-transcription model. 60 languages with automatic detection and Hinglish code-switching, up to 2 hours per file. $0.375 per audio hour.

Speech to Text

MAI-Transcribe-2

Powered by Microsoft · Speech recognition (Microsoft AI)

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Speech to Text

Overview

MAI-Transcribe-2 is a preview speech-to-text model from Microsoft AI. It transcribes recorded audio on POST /v1/audio/transcriptions; it is not available in voice sessions, and POST /v1/audio/translations refuses it.

It covers 60 languages and detects the language automatically when none is set, including Hinglish and other code-switching. Set language to a single code if you want to pin it; hi and hi-IN both work, and a language outside the list returns 400. A file can run up to 2 hours, within the route's 25 MB upload limit. WAV, MP3, FLAC and Ogg are accepted.

Preview: Microsoft ships this model without an SLA and may change or retire it at short notice. If it is retired, the ID keeps working and is answered by a named successor, so transcripts may differ. Use a generally available model for production-critical workloads. It is not processed in India, is paid-plan only and is never a default.

Pricing

MetricPrice
Price /hour₹36.0000

1 credit = ₹1 ≈ US$0.0104 (US$1 = ₹96). Transparent per-call pricing — you pay only for what you call, with no per-seat charge or minimums.

Key Highlights

  • Preview model from Microsoft AI
  • 60 languages with automatic language detection
  • Handles Hinglish and other code-switching
  • Up to 2 hours of audio per file

Benchmarks

BenchmarkScore
Languages60
Price$0.375
Max audio2 hours
StatusPreview

Technical Details

  • File transcription only — not available in voice sessions
  • Not translate-capable — POST /v1/audio/translations refuses it
  • language takes one code (hi and hi-IN both work); an unlisted language returns 400
  • WAV, MP3, FLAC and Ogg input
  • response_format: json, text or verbose_json
  • Not processed in India

Strengths

  • 60 languages with automatic detection
  • Code-switching support
  • Up to 2 hours per file

Limitations

  • Preview — no SLA; may change or be retired at short notice
  • File transcription only — no voice sessions or translation
  • Not processed in India
  • Paid plans only

Use Cases

Long recordings and meetingsMultilingual and Hinglish call transcriptionBatch transcription of recorded calls

API Example

curl https://api.callmissed.com/v1/audio/transcriptions \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -F model=mai-transcribe-2 \
  -F [email protected]

Endpoint: POST /v1/audio/transcriptions · Model ID: mai-transcribe-2

Try MAI-Transcribe-2 now

Get 1000 free API credits on signup. No credit card required.

Start free Book a DemoRead docs