Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | kotoba-technologiesKotoba Speech-to-TextRemove × |
|---|---|
| What’s different | Transcribes clips up to two minutes with optional word timings and speaker labels; includes Japanese and Chinese variants. |
| Date | Oct 9, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.0041666667/ minutefal · all routes ↗Input audio minute |
| Provider endpoints | 1 endpoint → |
Specifications | |
| Context window | — |
| Max output | — |
| Parameters | — |