New Transcription Model Released

We've released T3 - our latest transcription model.

With this update, you should see a further improvement in AI transcripts. Our engine can now spell company and people names better than it could in the past.

Overall transcript quality also gets an improvement.

You can also assist the AI by entering words that you would like it to pay attention to in the Glossary section.


Our tests indicate that our model now outperforms all other major general-purpose speech-to-text engines. Since our model is built for knowledge-heavy B2B content, it performs better than general models.


We will continue making improvements to the model with updates like the website parser that can learn important terms from your website without the need to manually update the glossary.

Did this answer your question? Thanks for the feedback There was a problem submitting your feedback. Please try again later.

Still need help? Contact Us Contact Us