Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | fish-audioFish Audio: S2 ProRemove × | togethercomputerTogether: Tev1 4B ExperimentalRemove × |
|---|---|---|
| What’s different | S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion. | Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24... |
| Date | Mar 10, 2026Released | Sep 30, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $0.042 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 0 endpoints → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Native Voice ↗Unversioned · provider native voices | 1,113.78 ↗Provider native voices · all categories · US + UK accents · 4 listed voicesIndependent result95% CI 1,101.78–1,125.78 · n=2,621 | Not reported |
Specifications | ||
| Context window | — | 32.8K |
| Max output | — | 8 |
| Parameters | — | 4B |
| Open weights | Supported | Supported |