Synthesia creates first interactive digital avatar for journalist using its own models
Synthesia, a video-generation startup valued at $4B, built an interactive digital avatar of journalist Alexandru Voica’s likeness. Trained on a specific article about venture fraud, the avatar uses Synthesia’s voice-to-text, language, and text-to-voice models to answer only questions tied to that topic. It took the company two days to create, combining photos, voice recordings, and AI-driven…
Key points
- Synthesia built an interactive digital avatar of journalist Alexandru Voica trained on one article about venture fraud
- Avatar uses Synthesia’s voice, language, and video models, with a deterministic response system tied to training data
- Creation took two days, but friends and family found the likeness and voice convincing yet imperfect
The avatar’s deterministic nature—it only responds to pre-trained queries—limited its usefulness beyond the chosen article. Friends found the voice and likeness convincing but not perfect, while Voica’s mother called it ‘amazing.’ Synthesia’s platform also offers non-interactive avatars for scripted content and an API for custom builds. The company sees potential in corporate training and media but acknowledges trust remains a barrier in journalism.
I created an interactive digital avatar of myself — and you can talk to it
TechCrunch AI · 26 September 2026
Loading the full article…
This text was published by TechCrunch AI and written by Dominic-Madori Davis. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
Comments
via GitHub Discussions