Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of zoom/scribe_v2_pro, Ideogram V4.5 Text to Image
2 modelszoomzoom/scribe_v2_proRemove ×ideogramIdeogram V4.5 Text to ImageRemove ×
What’s different11 languagesGenerate high-quality images, posters, and logos with Ideogram 4.5, with accurate text rendering and low, medium, or high quality tiers.
DateOct 17, 2026DiscoveredSep 30, 2026Released
Listed rateSee provider quotesSee provider quotes
Provider endpoints0 endpoints →1 endpoint →
AA Image ↗2.1Not reported1,015.68 ↗Text-to-image · all categories · quality=highIndependent result95% CI 1,000.68–1,030.68 · n=2,634
AMI-Cleaned WER ↗English short-form; normalization unversioned6.08% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned4.12% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned7.75% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
LS Clean WER ↗English short-form; normalization unversioned1.11% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
LS Other WER ↗English short-form; normalization unversioned2.24% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
SPGISpeech WER ↗English short-form; normalization unversioned1.36% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
URGENT2024 WER ↗English short-form; normalization unversioned7.99% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
Voice Arena Monsoon WER ↗English short-form; normalization unversioned3% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned3.08% WER ↗zoom/scribe_v2_proLeaderboard entryNot reported
Context window——
Max output——
Parameters——
Audio inputSupportedNot reported
TranscriptionSupportedNot reported

Add another model

Search all models →