Speaker
Description
VoxBento: Reimagining Real-Time Multilingual Interpretation with AI
What if professional event interpretation did not require dedicated booths, complicated hardware, or specialized listening devices?
VoxBento is an open source, browser-first platform for real-time multilingual interpretation, combining WebRTC-based media infrastructure with speech recognition, context-aware AI translation, live subtitles, and AI-generated speech.
This talk goes behind the scenes of VoxBento, covering its low-latency audio pipeline, seamless interpreter handoffs, AI translation and synthesis, browser-based attendee experience, and the architecture required to securely support multiple events.
We will explore how human interpreters and AI can work together rather than treating AI as a simple replacement, and how modern real-time infrastructure can make multilingual communication more accessible and scalable.
The session concludes with a live demonstration of VoxBento and a look at the future of open source, AI-powered accessibility.
Audience: Developers, students, researchers, open source contributors, and engineers interested in real-time systems, WebRTC, AI/ML, accessibility, and open source infrastructure.
No prior knowledge of speech AI or WebRTC is required.
Any other info we should know?
This is a technical talk aimed at developers interested in AI, distributed systems, and open source.
Happy to provide a live demonstration during the session. An offline recording will be available as backup.
The audience will learn:
How real-time multilingual interpretation systems work
Designing low-latency streaming architectures using WebRTC
Integrating speech recognition, translation, and text-to-speech providers
Lessons learned while building VoxBento as a GSoC 2026 project under FOSSASIA
Opportunities to contribute to the project
The presentation includes architecture diagrams, live demonstrations, and discussion of real engineering challenges encountered during development. Basic familiarity with web development is helpful but not required.
Session author's bio
I'm Arnav Angarkar, a Computer Science student at IIIT Dharwad and an open source contributor with FOSSASIA. My work primarily focuses on AI infrastructure, developer tools, and scalable web applications.
As a Google Summer of Code 2026 contributor, I developed major components of VoxBento, an open source real-time multilingual interpretation platform that combines speech recognition, machine translation, and speech synthesis for live events. I also actively contribute to Eventyay, FOSSASIA's open source event management platform, where I've worked across both backend and frontend systems.
I'm passionate about building practical open source software that improves accessibility and enables communities worldwide to collaborate across language barriers. I enjoy sharing engineering lessons from real-world projects and helping new contributors get involved in open source.
| Please confirm that there are included headshots of all speakers in their profiles | Yes |
|---|---|
| Level of Difficulty | Intermediate |
| In Person Attendance | Remote |
| Agree to Privacy Policy and Notice | I agree |
| Social Media | https://x.com/ArnavA_0824 |