WHAT IT IS
Synthesia is an enterprise video generation platform the London-based company Synthesia launched in 2019: you enter text and get a video of a digital presenter delivering it. It targets scenarios such as corporate training, product explainers and internal communication, and can produce the same script in multiple languages. Synthesia is delivered as a web application, with built-in or customized presenter avatars.
Why it matters
It was early to make presenter-avatar videos something enterprises could produce at scale, a clear path toward commercializing digital-human video.
Key specs
- Form
- Web application
- Avatars
- Built-in or customized digital presenters
- Modality
- Text in; video out
Capabilities
Related concepts
Multimodal Generation
One model that learns to speak, to draw, to move — even to model the 3D world
Inference Optimization & Serving
Training happens once; inference happens a billion times a day — and serving is torn between fast first tokens and high throughput, which usually pull against each other
Comparable products
Sora
2024Generates coherent video up to about a minute long from a description
Veo
2024Generates 1080p video clips with coherent shots
SenseAvatar
2022Generates lip-synced digital-human video from a portrait and a voice track