Fact · Speech recognition
Artificial Analysis says a speed factor above 1 means the service transcribes faster than real time, so 2.0 means 10 minutes of audio is transcribed in 5 minutes.
Checked against its source on October 17, 2026
In the source's own words
“A value above 1 means the service transcribes faster than real time”
Speech to Text Benchmarking Methodology (Artificial Analysis), Artificial Analysis, Artificial Analysis, n.d., Speed Factor (batch).
Open the original- What it measures
- The speed factor is audio duration divided by API response time, and the batch benchmark includes network latency.
- What it does not show
- A throughput measure for batch transcription, not the wait before a live word appears.