Speech benchmarks
Plain sentence
Why we chose this prompt: A short everyday sentence with a proper noun and two spoken-out times. It is the baseline: if a model drops, adds or changes a word here, nothing else it does matters.
Prompt
Route 6 Espresso is open till nine, and the last train leaves at eleven fifty-six.
Sort by
provider default
Cost--Generation time1.7sCorrectness100%provider default
Cost--Generation time13.7sCorrectness100%tara
Cost--Generation time6.3sCorrectness100%
aura-2-thalia-en
Cost$0.002Generation time1.5sCorrectness100%flux-alexis-en
Cost--Generation time4.0sCorrectness100%george
Cost--Generation time0.6sCorrectness100%george
Cost--Generation time0.5sCorrectness100%george
Cost--Generation time2.2sCorrectness100%george
Cost--Generation time0.6sCorrectness100%george
Cost--Generation time1.9sCorrectness100%george
Cost--Generation time2.4sCorrectness100%george
Cost--Generation time1.9sCorrectness100%george
Cost--Generation time1.9sCorrectness100%george
Cost--Generation time1.5sCorrectness100%provider default
Cost--Generation time1.3sCorrectness100%provider default
Cost$0.001Generation time0.7sCorrectness100%provider default
Cost$0.001Generation time1.2sCorrectness100%provider default
Cost$0.001Generation time0.9sCorrectness100%
Zephyr
Cost--Generation time3.6sCorrectness100%Zephyr
Cost--Generation time2.9sCorrectness100%
af_alloy
Cost$0.000051Generation time0.5sCorrectness100%nadine
Cost--Generation time2.9sCorrectness100%nadine
Cost--Generation time8.9sCorrectness100%
en-US-Harper:MAI-Voice-2
Cost--Generation time1.2sCorrectness100%cs-CZ-Grant:MAI-Voice-2.1
Cost--Generation time1.5sCorrectness100%cs-CZ-Grant:MAI-Voice-2.1-Flash
Cost--Generation time0.7sCorrectness100%en-US-Harper:MAI-Voice-2
Cost$0.001Generation time1.9sCorrectness100%English_expressive_narrator
Cost$0.008Generation time1.2sCorrectness100%English_expressive_narrator
Cost--Generation time1.0sCorrectness100%
voice_3150
Cost--Generation time1.6sCorrectness100%
loongjohn
Cost$0.001Generation time2.0sCorrectness100%eve
Cost$0.001Generation time1.1sCorrectness100%conversational_a
Cost--Generation time67.5sCorrectness95%Zephyr
Cost--Generation time3.6sCorrectness90%en_paul_sad
Cost$0.000Generation time5.0sCorrectness89%longanlingxin
Cost$0.002Generation time1.9sCorrectness89%geffen_32
Cost--Generation time1.8sCorrectness--