benchmarks.site

Public leaderboard · Speech recognition (ASR)

Artificial Analysis Speech to Text

Compares services that turn spoken audio into written text: how many words they get wrong, how fast they are and what they cost.

Leaderboard

What it measures

Compares hosted and open speech-to-text models on word error rate together with speed and price.

How to read the numbers

Word error rate: share of words transcribed wrongly (%), lower is better — lower is better.

Results

The publisher does not allow copying its results, so they are not reproduced here. Artificial Analysis Terms of Use (sec. 2.2(d)): 'except as expressly stated herein, no part of the Site may be copied, reproduced, distributed, republished...'; the Acceptable Use Policy also bans scraping. Their data platform page says external redistribution requires a commercial package. Rows left empty for that reason; see the live leaderboard at the source URL.

Note: Artificial Analysis Terms of Use (sec. 2.2(d)): 'except as expressly stated herein, no part of the Site may be copied, reproduced, distributed, republished...'; the Acceptable Use Policy also bans scraping. Their data platform page says external redistribution requires a commercial package. Rows left empty for that reason; see the live leaderboard at the source URL.

Source: Artificial Analysis · artificialanalysis.ai · retrieved 2026-11-17 · license: proprietary (Terms of Use prohibit copying/redistribution)

Markdown · More Speech recognition (ASR)