Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | googleGoogle: Gemini 3.8 Flash TTSRemove × | openaiwhisper-large-v3Remove × |
|---|---|---|
| What’s different | Separates spoken text from delivery instructions; supports exactly two named speakers with ordered dialogue turns. | Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech… |
| Date | Sep 23, 2026Released | Jul 17, 2024Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.045/ 1K charactersfal · all routes ↗ | $7.50 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → | 2 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Native Voice ↗Unversioned · provider native voices | 1,275.38 ↗Provider native voices · all categories · US + UK accents · 8 listed voicesIndependent result95% CI 1,260.38–1,290.38 · n=2,783 | Not reported |
| AMI-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 13.63% WER ↗openai/whisper-large-v3Leaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | Not reported | 7.99% WER ↗openai/whisper-large-v3Leaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 8.35% WER ↗openai/whisper-large-v3Leaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | Not reported | 1.56% WER ↗openai/whisper-large-v3Leaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | Not reported | 3.52% WER ↗openai/whisper-large-v3Leaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | Not reported | 2.71% WER ↗openai/whisper-large-v3Leaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | Not reported | 13.73% WER ↗openai/whisper-large-v3Leaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | Not reported | 3.95% WER ↗openai/whisper-large-v3Leaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 4.53% WER ↗openai/whisper-large-v3Leaderboard entry |
Specifications | ||
| Context window | 32.8K | — |
| Max output | 16.4K | — |
| Parameters | — | — |
| Audio input | Not reported | Supported |
| Transcription | Not reported | Supported |
| Open weights | Not reported | Supported |