Tincans

We're building real-time conversational speech with large language models. Bots should be fun to talk to.

Previously, we built large scale machine learning systems at Cash App, Quora, Airbnb, and more.

Every fortnight type beat.

NEW2024-04-17: We've released a demo of 500ms low-latency voice chat.
2024-04-03: We enjoyed the cherry blossoms in NYC.
2024-03-19: We've released a stronger joint speech-language model and live demo. Read our technical report or get the weights on Hugging Face.
2024-03-06: We've released a research preview of our joint speech-language model.
2024-02-16: We've validated our joint speech-language modeling approach. Read more in our report.

We're building with a select number of alpha partners. If you're interested in learning more, we'd love to hear from you.