toby

toby is a desktop application that provides real-time speech translation during video calls. It acts as a live AI interpreter, capturing audio from your computer's system and translating conversations bidirectionally between 15 different languages. The tool works by processing the audio from any video call platform—including Zoom, Teams, Slack, Meet, and others—and delivering translated speech with minimal delay, effectively breaking down language barriers during live conversations.

What sets toby apart is its comprehensive approach to real-time translation. It provides both spoken translations and written transcripts of what's being said and heard, ensuring nothing gets lost in translation. Users can create personalized glossaries for industry-specific terms or unique vocabulary, and customize their experience with voice preferences, translation model selection, and volume controls. The tool has already been trusted to power over 5,000 calls at organizations like Columbia University and Talkdesk.

This tool is particularly valuable for international business teams, professionals working with global clients, and multilingual families who need seamless communication across language barriers. Whether you're conducting cross-border negotiations, collaborating with international colleagues, or simply connecting with relatives who speak different languages, toby eliminates the need for human interpreters and makes multilingual conversations feel natural and effortless.