# MAI-Transcribe-2-Streaming Benchmark Scores & Performance

> MAI-Transcribe-2-Streaming has MAI-Transcribe-2-Streaming launch notes results. Voice evidence is display-only and does not produce a text-model score.

Canonical page: https://benchlm.ai/models/mai-transcribe-2-streaming

Last updated: October 1, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Microsoft |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [Microsoft model documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe-2-streaming) |
| Overall Score | Not scored (voice evidence only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: MAI-Transcribe-2-Streaming
- Variant: base
- Benchmarks covered: 0 of 645
- Coverage note: Speech and voice results appear below; no weighted text-model benchmark rows are stored.

## Speech and voice evidence

[MAI-Transcribe-2-Streaming launch notes](/voice-benchmarks/mai-transcribe-2-streaming-launch-notes)

Microsoft reports first hypotheses just over 100 ms after receiving audio. That timer differs from transcript latency measured after detected speech end. The non-streaming model's FLEURS result does not establish this streaming release's accuracy.

| Metric | Result |
| --- | --- |
| Coverage | Evaluated system |
| Owner label | MAI-Transcribe-2-Streaming |
| Result source | Official paper |

Participant or pipeline component identified from the benchmark paper; no weighted BenchLM score is assigned.

- [Evaluation source](https://microsoft.ai/news/our-first-streaming-transcription-model/)

Released October 1, 2026. Microsoft reports 60 languages and continuous automatic language detection. Azure documents public-preview access through its Realtime-compatible WebSocket API and Speech SDK. The launch also lists MAI Playground, Vercel, and Azure Voice Live; LiveKit is coming soon.

## Other Microsoft Models

- [Phi-4](/models/phi-4) - Score: 26.37
- [MAI-Thinking-1](/models/mai-thinking-1) - Score: not computed
- [MAI-Code-1.1-Flash](/models/mai-code-1-1-flash) - Score: not computed
- [Raw Phi-4 mini direct logits](/models/raw-phi-4-mini) - Score: not computed
- [Fara1.5-27B](/models/fara-1-5-27b) - Score: not computed
- [Fara1.5-4B](/models/fara-1-5-4b) - Score: not computed
- [MAI-Voice-2.1](/models/mai-voice-2-1) - Score: not computed
- [MAI-Voice-2.1-Flash](/models/mai-voice-2-1-flash) - Score: not computed
- [MAI-Transcribe-2](/models/mai-transcribe-2) - Score: not computed
- [VibeVoice-ASR-Streaming 1.5B](/models/vibevoice-asr-streaming-1-5b) - Score: not computed
- [VibeVoice-ASR-Streaming 7B](/models/vibevoice-asr-streaming-7b) - Score: not computed
- [MAI-Cyber-1-Flash](/models/mai-cyber-1-flash) - Score: not computed
- [MAI-Voice-2-Flash](/models/mai-voice-2-flash) - Score: not computed
- [MAI-Transcribe-1.5](/models/mai-transcribe-1-5) - Score: not computed
- [MAI-Voice-2](/models/mai-voice-2) - Score: not computed
- [Phi-4 Multimodal Instruct](/models/phi-4-multimodal-instruct) - Score: not computed