AssemblyAI
The best way to build Voice AI apps with one robust API
Start new thread
Meredith Rauch

Universal-1 - Multilingual speech AI model trained on 12.5M hours of data

by
AssemblyAI
•
Try AssemblyAI's most capable and highly trained speech recognition model trained on 12.5M hours of multilingual audio data. Universal-1 achieves best-in-class speech-to-text accuracy, reduces word error rate and hallucinations, and improves timestamps.

Add a comment

Replies

Best
Brandon
Congratulations on the launch! It's fantastic to see your product achieving a higher accuracy in voice recognition than many big companies. It's truly impressive and admirable. In the future, if my product development involves voice recognition, I will definitely consider using your API!
Bon
Congrats on the launch of Universal-1!
Amy Yan
Great launch, AssemblyAI! 🚀 Universal-1's focus on multilingual speech recognition and improving accuracy is exactly what the industry needs. This model will make a huge difference in developing global voice applications. Excellent job!
William Jin
Great launch! How does Universal-1 handle multilingual support and accuracy across different languages?
First
Previous
12