Funding
Funding not disclosed
Founders
Product
Problem
Language barriers during video calls and live streams prevent seamless communication, limiting collaboration and audience engagement for monolingual speakers.
Solution
SpokeTek offers AI-driven real-time visual translation dubbing that overlays translated captions and synchronized audio onto participants' video feeds. Its Digital Twinterpreters use a Multilingual Augmented Reality (M‑LAR) filter to generate mouth‑movement animations (visemes) that match the translated speech, creating the illusion of a native speaker. The service is available through a social networking app for consumer use and as a B2B plugin API that can be integrated into existing videoconferencing platforms. By delivering both visual and auditory translations instantly, SpokeTek enables users to converse and consume content across languages without manual interpretation.
Target Audience
Primary users are individual speakers and live streamers who need instant multilingual communication, as well as enterprises and platform providers seeking to add real-time translation dubbing to their video services.
Features
- AI-powered translation engine supporting multiple languages with low-latency processing
- Multilingual Augmented Reality filter that generates synchronized viseme animations aligned to translated speech
- Real-time caption overlay with adjustable styling for accessibility
- Audio dubbing that matches the visual mouth movements for a cohesive interpreter experience
- Consumer-facing social networking app with built‑in video conferencing and translation capabilities
- B2B plugin API allowing third‑party platforms to embed the Digital Twinterpreter technology