Nonverbal cue
Why we chose this prompt: Parenthetical cues like (sighs) and (laughs) ask for a sound, not a word. This checks whether the model produces the nonverbal, skips it, or reads the cue text out loud.
Prompt
(sighs) Route 6 Espresso is open till nine. (laughs) The last train leaves at eleven fifty-six.
Sort by
provider default
Cost--Generation time41.3sCorrectness100%george
Cost--Generation time2.2sCorrectness100%george
Cost--Generation time1.9sCorrectness100%george
Cost--Generation time2.0sCorrectness100%george
Cost--Generation time1.6sCorrectness100%provider default
Cost$0.001Generation time1.4sCorrectness100%provider default
Cost--Generation time1.2sCorrectness100%English_expressive_narrator
Cost$0.009Generation time1.0sCorrectness100%
longanlingxin
Cost$0.002Generation time2.1sCorrectness100%eve
Cost--Generation time1.2sCorrectness100%
Zephyr
Cost$0.004Generation time3.9sCorrectness95%
cs-CZ-Grant:MAI-Voice-2.1-Flash
Cost--Generation time2.3sCorrectness95%English_expressive_narrator
Cost$0.006Generation time1.1sCorrectness95%cs-CZ-Grant:MAI-Voice-2.1
Cost--Generation time2.6sCorrectness90%loongjohn
Cost$0.001Generation time1.6sCorrectness84%
flux-alexis-en
Cost--Generation time7.1sCorrectness79%george
Cost--Generation time0.9sCorrectness75%george
Cost--Generation time1.3sCorrectness75%george
Cost--Generation time3.3sCorrectness75%george
Cost--Generation time2.3sCorrectness75%george
Cost--Generation time2.0sCorrectness75%
af_alloy
Cost--Generation time0.6sCorrectness75%en-US-Harper:MAI-Voice-2
Cost--Generation time1.7sCorrectness75%en-US-Harper:MAI-Voice-2
Cost--Generation time1.6sCorrectness75%
en_paul_sad
Cost--Generation time4.8sCorrectness75%conversational_a
Cost--Generation time122.7sCorrectness68%provider default
Cost$0.001Generation time0.6sCorrectness65%tara
Cost$0.00067Generation time8.6sCorrectness62%aura-2-thalia-en
Cost$0.003Generation time3.2sCorrectness62%- Google AI Studio
Zephyr
Cost$0.002Generation time5.5sCorrectness-- Zephyr
Cost--Generation time3.9sCorrectness--