Fact · Speech recognition
0.5real-time factor
In Microsoft's worked example, a device that processes a one-minute audio file in 30 seconds has a real-time factor of 0.5.
Checked against its source on October 17, 2026
In the source's own words
“if a device processes a 1-minute audio file in 30 seconds, the RTF is 0.5”
Embedded speech performance evaluations (Speech service), Microsoft Learn, n.d., Metrics & terminology.
Open the original- What it measures
- The example is a teaching illustration in the metrics section, not a measured result for a named device.
- What it does not show
- An arithmetic example, not a benchmark. Real files vary in speed with model size, audio length and hardware.