Live Captions by Subanana delivers real-time speech transcription and translation for events and classes, projecting timecoded text to screens and attendee mobile devices.
What the product does and how it is positioned
Live Captions by Subanana provides automated real-time speech recognition and live translation designed for keynotes, lectures, webinars, and public presentations.
The platform converts spoken audio into millisecond-timecoded captions as speech happens, supports pre-loaded speaker rosters and domain glossaries, and shares synchronized text to room displays and attendee smartphones.
Source-supported ways to use the product
Event organizers project live captions onto main venue displays while international attendees follow translations on their smartphones via QR code.
Instructors deliver lectures with live multilingual captioning and instantly access an automatically compiled transcript once the presentation ends.
The documented workflow, where available
Pre-load speaker identities, expected participant rosters, and specialized terminology into the event console.
Capture spoken speech in real time, projecting captions to room screens and distributing them to attendee phones via QR code.
Access the automatically accumulated transcript archive and download finished files in formats such as SRT, VTT, or DOCX.
Live Captions by Subanana processes spoken audio as it happens, generating timecoded lines without requiring pre-recorded file uploads or text prompts. Spoken lines draft and settle continuously, forming a complete record while presenters speak.
The system supports simultaneous output to venue displays and attendee mobile devices. Audience members can join the live feed by scanning a projected QR code or following a host link, allowing them to read along in supported languages such as English or Cantonese on their own screens.
Checks to run with your own material and workflow
What was checked and when
Answers based on the source-checked product record
Attendees can point their device cameras at an on-screen QR code or open a shared link from the host to stream live captions directly within their mobile browsers.
Yes, organizers can pre-load speaker rosters and custom glossary terms into the event console so that technical vocabulary and names are applied during live captioning.
The platform automatically archives settled caption lines and allows exporting to SRT, VTT, DOCX, TXT, XLSX, Markdown, and burned-in MP4 video files.
Users can employ a calendar-aware bot that joins meetings or use a Chrome extension that captures tab audio directly without placing an entry in the participant list.
The platform supports more than 95 languages, including multilingual and code-switched speech such as Cantonese and English, with live translation capabilities.
