TRADE: Transducer-Augmented Decoder for Speech LLM

Most speech AI models can’t respond while you’re still talking — they lose track of the audio as it arrives, so real-time conversation breaks down. TRADE pairs the language model with a streaming component that follows your words live, so one model can keep up in real time and know exactly when you’ve finished speaking. Built with speech researchers at Carnegie Mellon.

Sign up for our newsletter.

Get our clinical outcomes, case studies, new AI agents, LLM updates, and more in your inbox.