Nova-3 от Deepgram устанавливает новые стандарты точности в распознавании речи даже в сложных акустических условиях. Это первая ИИ-модель, обеспечивающая мультиязычную транскрибацию в реальном времени с возможностью мгновенной настройки под специфический словарь пользователя.
Nova-3 advances Deepgram's industry-leading accuracy, extending its capabilities to a broader range of real-world enterprise use cases and challenging audio conditions. Nova-3 is the first voice AI model to offer real-time multilingual transcription. Our latest model is also the first to provide users with demonstrably effective and highly accurate self-serve customization—enabling instant vocabulary adaptation without model retraining. Superior accuracy: Nova-3 delivers industry-leading performance with a 54.3% reduction in word error rate (WER) for streaming and 47.4% for batch processing compared to competitors. Preferred for multilingual support: Deepgram was preferred over Whisper on 7 out of 7 languages tested—reaching as high as an 8-to-1 preference on certain languages.