MAI-Transcribe
Audio Preview Full comparison ↗ microsoft-azure/mai-transcribe · by Microsoft AI
· llm-based-asr
Pricing — 1 offering(s)
LLM Speech transcription
- $0.0060 / minute Current 2026-04-02 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
See how MAI-Transcribe fits into a cost-aware routing setup
See how →Capability profile
Benchmarks
| Benchmark | Score | Config | Source |
|---|---|---|---|
| WER (FLEURS, 25 languages — MAI-Transcribe-1, Microsoft-reported) | 3.86 % | Mean WER across MAI-Transcribe-1's 25 supported languages. Microsoft reports it as the lowest average against Scribe v2, Whisper-large-v3, GPT-Transcribe and Gemini 3.1 Flash on the same 25-language set. | source ↗ |
| WER (Artificial Analysis Speech-to-Text leaderboard — independent) | — | MAI-Transcribe-1.5 listed at 2.4% WER, MAI-Transcribe-1 at 2.6%, under Microsoft/Azure. AA's own evaluation set, not FLEURS — directionally consistent with Microsoft's best-in-class claim. | source ↗ |
Operator guidance
Reach for MAI-Transcribe when you want strong published multilingual accuracy at a low price ($0.36/hour, ~2.8x cheaper than Azure Cognitive Services Speech-to-Text at $1.00/hour) and your workload is file-based. It is in public preview with no SLA, so it is not a fit for production workloads that need contractual guarantees — use microsoft-azure/speech-stt or Deepgram Nova-3 there. It also has no speaker diarization and no real-time streaming; route to speech-stt, Nova-3, or Amazon Transcribe for those. Its closest accuracy peers are OpenAI GPT-Transcribe and ElevenLabs Scribe v2. Only MAI-Transcribe-1.5 should be used — MAI-Transcribe-1 was deprecated on 20 Aug 2026.
Use cases
- Multilingual video captions and subtitling
- Meeting and call-centre transcription where FLEURS-grade multilingual accuracy matters
- Accessibility transcripts for audio and video content
- Transcription model inside Azure Voice Live voice agents
- Cost-sensitive batch transcription (~2.8x cheaper than the Azure Cognitive Services STT API)
Limitations
- Public preview — no SLA, not recommended for production workloads (Azure Learn doc)
- No speaker diarisation in either version
- No real-time streaming — file input only (WAV/MP3/FLAC, <300 MB per request)
- MAI-Transcribe-1 deprecated 20 Aug 2026; only MAI-Transcribe-1.5 is current
- 43 languages (1.5) / 25 (1) — narrower than the Azure Cognitive Services STT service's 100+ locales
- Served only in East US and West US regions at preview
- Billed via the 'LLM Speech' SKU, which currently shares a price/SKU ID with Azure Fast Transcription
- FLEURS WER figures are Microsoft-reported; the independent Artificial Analysis numbers use a different evaluation set