# MAI-Transcribe-2-Streaming on AA-WER: Voice Benchmark Profile

> Artificial Analysis reports 2.5% word error rate for final and first-partial transcripts from MAI-Transcribe-2-Streaming.

- Scope: One exact Microsoft AI hosted configuration captured October 1, 2026; AA-AgentTalk, VoxPopuli, and Earnings22
- Measurement lanes: Voice experience, Latency
- Primary metric: Word error rate in percent and latency after speech end in seconds; lower is better
- Available evidence: Exact evaluator payload retained in private evidence; percentages rounded to one decimal and seconds to two decimals
- Owner: Artificial Analysis
- Source snapshots refreshed: 2026-10-28

## Interpretation limit

This single configuration capture does not mirror the full leaderboard. The index weights AA-AgentTalk at 50%, VoxPopuli at 25%, and Earnings22 at 25%. Latency starts at SileroVAD-detected speech end; first partial is the first transcript-bearing event afterward. Missing endpoint finals can use the documented partial fallback. Evaluation date, hardware, and confidence intervals are not published in this row. The capture date does not establish when the evaluation ran.

## Primary sources

- [Owner page](https://artificialanalysis.ai/speech-to-text/streaming)

Canonical page: https://benchlm.ai/voice-benchmarks/aa-wer-streaming-mai-transcribe-2