Live Captions for Any Conference & Event

Our AI-powered system aims for high accuracy. Initial Speech-to-Text (STT) performance typically ranges from 87.9% to 98.4% depending on the language. Please note that the final accuracy of the translated captions and spoken audio is influenced by the quality of the original audio, the specific language pair, and the complexity of the speech.

For reliable, low-latency performance, we recommend a dedicated, stable internet connection with a minimum of 1 Mbps upstream and 1 Mbps downstream per active translation session. Consistent, wired connections are highly preferred over venue Wi-Fi.

Yes, absolutely. You can use the same account on multiple separate laptops at the same time. This allows you to connect each device to a different screen, confidence monitor, or projector, providing live captions for multiple viewing areas from a single session.

Usage is calculated based on a credit system: 5 credits equal 60 minutes of live translated captions for one language. This means if you are translating one source language into two target languages simultaneously (e.g., English to Spanish and French), the consumption rate will be double (10 credits per 60 minutes). Your balance never expires.

Yes, security and privacy are paramount. We only store the transcripts of the original and translated languages for accessibility. All deleted transcripts are permanently removed from our systems. Our underlying speech-to-text and translation technology partners do not retain or store any of your data.

Yes. Your session transcripts are automatically saved in the original language and all translated languages. They are easily accessible for review and export in your account's Transcripts section. Please note that the translated audio output itself cannot be saved.