Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | Wan-AIWan2.7-R2VRemove × | assemblyaiAssemblyAI: Universal-3.5 ProRemove × |
|---|---|---|
| What’s different | Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation. | Universal-3.5 Pro is AssemblyAI's speech-to-text model served through its Sync API, returning a complete transcript with word-level timestamps in a single synchronous response for audio clips up to 120… |
| Date | Apr 27, 2026Listed | Sep 22, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output second | $83.3333 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | ||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 10.63% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | Not reported | 6.05% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 7.62% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | Not reported | 1.1% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | Not reported | 2.11% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | Not reported | 1.81% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | Not reported | 9.08% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | Not reported | 3.49% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 1.92% WER ↗assemblyai/universal-3-5-proLeaderboard entry |
Specifications | ||
| Context window | — | — |
| Max output | — | — |
| Parameters | — | — |
| Audio input | Not reported | Supported |
| Transcription | Not reported | Supported |