Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | openaiwhisper-large-v3Remove × | bosonaibosonai/higgs-audio-v3-sttRemove × |
|---|---|---|
| What’s different | 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… | 2.68B parameters · 1 language · Encoder: Whisper · Decoder: Qwen3 |
| Date | Jul 17, 2024Listed | Oct 17, 2026Discovered |
API prices USD · provider configuration shown below | ||
| Listed rate | $7.50 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | See provider quotes |
| Provider endpoints | 2 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 13.63% WER ↗openai/whisper-large-v3Leaderboard entry | 7.19% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 7.99% WER ↗openai/whisper-large-v3Leaderboard entry | 7.04% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 8.35% WER ↗openai/whisper-large-v3Leaderboard entry | 7.45% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | 1.56% WER ↗openai/whisper-large-v3Leaderboard entry | 1.08% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | 3.52% WER ↗openai/whisper-large-v3Leaderboard entry | 2.61% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | 2.71% WER ↗openai/whisper-large-v3Leaderboard entry | 2.07% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | 13.73% WER ↗openai/whisper-large-v3Leaderboard entry | 11.88% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 3.95% WER ↗openai/whisper-large-v3Leaderboard entry | 3.97% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 4.53% WER ↗openai/whisper-large-v3Leaderboard entry | 3.73% WER ↗bosonai/higgs-audio-v3-sttLeaderboard entry |
Specifications | ||
| Context window | — | — |
| Max output | — | — |
| Parameters | — | 2.68B |
| Audio input | Supported | Supported |
| Transcription | Supported | Supported |
| Open weights | Supported | Not reported |