AI startup Synthesia has unveiled several new product updates.
The company has introduced the ability to create AI-generated avatars by recording less than five minutes of footage with a webcam or phone,
Additionally, you can clone your voice, enabling the avatars to speak in multiple languages.
Artificial intelligence startup Synthesia has unveiled several new product updates including a feature that allows users to create Apple-style key presentations with AI avatars using only a laptop webcam or a phone.
Let’s take a closer look at the details.
Also read: Nvidia’s G-Assist AI aims to enhance your PC gaming experience: Here’s how
The seven-year-old firm, backed by Nvidia, announced that the new product updates will transform it into a comprehensive video production suite for large companies, moving beyond its original focus on creating AI-generated avatars.
Also read: Google DeepMind’s new AI can generate audio for videos: Here’s how it works
One of the most significant new features the firm showcased is the ability to create AI-generated avatars by recording less than five minutes of footage with a webcam or phone, reports CNBC. Additionally, you can clone your voice, enabling the avatars to speak in multiple languages.
For those who are unaware, typically, creating an AI avatar using Synthesia’s platform requires an in-person studio visit. Human actors enter a recording booth, record their voices, and perform lines in front of a green screen on a film set. This process provides training data for Synthesia’s AI algorithm to capture the facial and vocal nuances necessary for generating human-like avatars that speak expressively. Earlier this year, Synthesia introduced new expressive avatars capable of conveying emotions such as happiness, sadness, and frustration.
However, Synthesia has now introduced a new software that makes it easier for users to create a digital version of themselves from anywhere, using just a webcam and Synthesia’s software.
The company has also unveiled the ability to create full-body avatars, a significant upgrade from Synthesia’s current avatars, which are limited to a portrait view. With this new feature, users can visit a studio equipped with dozens of cameras, sensors, and lights to create avatars capable of moving their hands.
Generating hands has traditionally been challenging for AI, largely because hands are a small part of the human body and are not typically the focus in visual content.
Synthesia also introduced a feature that allows AI avatars to speak in any language, including English, French, German, and Chinese.
Synthesia also launched a new AI video assistant capable of producing summaries of entire articles and documents. Another significant feature being rolled out is a screen recording tool, where an AI avatar guides you through what you’re watching.
Follow Us
Ayushi Jain
Tech news writer by day, BGMI player by night. Combining my passion for tech and gaming to bring you the latest in both worlds. View Full Profile
