Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | nvidiaNemotron-3-DiarizationRemove × | googleembeddinggemma-2Remove × | openaiwhisper-large-v3Remove × |
|---|---|---|---|
| What’s different | Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call… | EmbeddingGemma 2 is a 740M parameter multimodal embedding model from Google DeepMind that maps text (incl. code), images, video and audio, alone or interleaved, into a single 768-dimensional vector space,… | 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 25, 2026Listed | Oct 8, 2026Listed | Jul 17, 2024Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.00001/ secondDeepInfra · all routes ↗Input audio second | See provider quotes | $7.50 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 2 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | Not reported | Not reported | 13.63% WER ↗openai/whisper-large-v3Leaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | Not reported | Not reported | 7.99% WER ↗openai/whisper-large-v3Leaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | Not reported | Not reported | 8.35% WER ↗openai/whisper-large-v3Leaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | Not reported | Not reported | 1.56% WER ↗openai/whisper-large-v3Leaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | Not reported | Not reported | 3.52% WER ↗openai/whisper-large-v3Leaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | Not reported | Not reported | 2.71% WER ↗openai/whisper-large-v3Leaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | Not reported | Not reported | 13.73% WER ↗openai/whisper-large-v3Leaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | Not reported | Not reported | 3.95% WER ↗openai/whisper-large-v3Leaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | Not reported | Not reported | 4.53% WER ↗openai/whisper-large-v3Leaderboard entry |
Specifications | |||
| Context window | — | 8.2K | — |
| Max output | — | — | — |
| Parameters | — | — | — |
| Audio input | Not reported | Not reported | Supported |
| Transcription | Not reported | Not reported | Supported |
| Open weights | Not reported | Not reported | Supported |