AssemblyAI's Universal 3.6 Pro speech model is live on Vapi

Vapi has integrated AssemblyAI's Universal 3.6 Pro speech model into its platform. According to Vapi, the model cuts background speech in transcripts by 30% and makes 45% fewer incorrect yes-or-no confirmations.

The model also holds conversational turns until complete phone numbers, verification codes, or email addresses are gathered, and adds support for 14 new languages with mid-sentence code-switching. Users can configure their agents with the new model directly in the [Vapi dashboard](https://dashboard.vapi.ai/).