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 × | googleGoogle: Gemini 3.8 Flash TTSRemove × |
|---|---|---|
| What’s different | Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation. | Separates spoken text from delivery instructions; supports exactly two named speakers with ordered dialogue turns. |
| Date | Apr 27, 2026Listed | Sep 23, 2026Released |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output second | $0.045/ 1K charactersfal · all routes ↗ |
| Provider endpoints | 1 endpoint → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Native Voice ↗Unversioned · provider native voices | Not reported | 1,278.21 ↗Provider native voices · all categories · US + UK accents · 8 listed voicesIndependent result95% CI 1,263.21–1,293.21 · n=2,806 |
Specifications | ||
| Context window | — | 32.8K |
| Max output | — | 16.4K |
| Parameters | — | — |