Benchmark › Speech models › Speed
Reported, not part of the overall score · updated 2026-11-22
Speed
How fast is audio produced, compared with its own length?
Word accuracyNumbers, dates and symbolsLong textRepeated wordsOther languagesEmotion controlReliabilitySpeed
Ranking
Seconds of audio produced per second of work. Higher is faster.
011×21×
What we test and how it is scored
Test. The 60 word-accuracy sentences.
Scoring. Median generation time, and audio length divided by generation time ("times real time"). For models called directly this is the full request time. For models reached through Replicate it is the compute time Replicate reports, which leaves out queueing. The two are not directly comparable, so speed is shown but never counted in the overall score.
Full item list and rules: methodology.
Think a score is wrong? Check it.
Every test item, scoring rule and known limit is published, and the audio behind each number is on the page.