Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | microsoftMicrosoft AI: MAI-Voice-2Remove × | openaiwhisper-large-v3-turboRemove × |
|---|---|---|
| What’s different | MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It… | Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper "Robust Speech Recognition via Large-Scale Weak Supervision" by Alec Radford et al.… |
| Date | Jun 2, 2026Listed | Oct 2, 2024Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $3.33 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 0 endpoints → | 3 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 13.88% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | Not reported | 8.09% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 8.47% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | Not reported | 2.13% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | Not reported | 3.71% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | Not reported | 2.79% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | Not reported | 13.69% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | Not reported | 4.77% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 7.02% WER ↗openai/whisper-large-v3-turboLeaderboard entry |
Specifications | ||
| Context window | — | — |
| Max output | — | — |
| Parameters | — | — |
| Audio input | Not reported | Supported |
| Transcription | Not reported | Supported |
| Open weights | Not reported | Supported |