# MAI-Transcribe-1.5 launch evaluation: Voice Benchmark Profile

> Microsoft’s June 2, 2026 Foundry post reports the FLEURS word error rate improvement for MAI-Transcribe-1.5 over MAI-Transcribe-1.

- Scope: FLEURS average WER over 25 languages and language coverage
- Measurement lanes: Voice experience
- Primary metric: Word error rate (lower is better)
- Available evidence: Exact figures published in the official Foundry post
- Owner: Microsoft AI
- Source snapshots refreshed: 2026-09-11

## Interpretation limit

Provider-reported results against Microsoft’s own previous model.

## Primary sources

- [Owner page](https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632)

Canonical page: https://benchlm.ai/voice-benchmarks/mai-transcribe-1-5-launch-evaluation