Speech benchmarks

Five nos, every model

The same prompt run across every live speech model in this category. Open any scenario to see the outputs side by side and what each run costs.

NormalizationDirections and units1 Invoice line1

ProsodyPunctuation3

FidelityFive nos1 Plain sentence1

CuesBracketed cue1 Nonverbal cue1

LanguageOther language3 Code switch1

LengthFull paragraph1 One word1

LiteralnessEmbedded instruction1

Text to AudioBenchmark17

Five nos

1 prompt17 models

Five nos · Fidelity

View collection

Looking for curated prompt sets instead? Browse collections · All benchmarks

Cookies keep FreeInd working. Optional analytics require your permission; ads for free accounts are served by Google, which shows its own consent message where required. Read our cookie policy.