Universal-1

Universal-1 is AssemblyAI's most powerful and accurate multilingual Speech AI model, trained on 12.5M hours of audio data. It offers industry-leading speech-to-text capabilities for voice data such as calls, virtual meetings, and podcasts, along with features like speaker detection, sentiment analysis, chapter detection, and PII redaction. The model achieves over 90% accuracy and makes up to 43% fewer errors on noisy data compared to other models.