AI video maker

Solution Introduction

Based on speech-to-animation and artificial intelligence technology developed by FaceUnity, a virtual presenter video with an accurate mouth shape, facial expressions and movements can be quickly produced with simple texts or audio materials. The practical application is broad and spans news broadcasting, educational courseware, event promotion, introduction to policies and other creative video production.

Solution Architecture

Applications

Media News Production

Educational courseware production

Event Promotion Video

Introduction to policies

Service Methods

Virtual Presenter SaaS Edition

Virtual Presenter API

Virtual Presenter Distribution Channel Edition

Virtual Presenter Private Edition

Core Functions

Presenter image selection / customization

3D image
2.5D image
Deep learning image
2D image

Effect setting

Single and double presenter switching
Speech content setting
Position re-sizing
Emotional action setting

Video Editing

Horizontal and vertical screen switching
Video background setting
Picture-in-picture content setting
Simultaneous captioning

Video rendering

Video content preview
Video content generation
Library management
Draft box management

Underlying technology

Image rendering

Speech-to-animation

Motion-driven avatar

Audio and video processing

Solution Features

Diverse virtual images

Six categories of virtual images in different styles and custom images tailored for different scenarios

Vivid and lifelike motion

Leading speech animation synthesis technology and intelligent expression algorithms applied to create lip-syncing virtual anchors with vivid facial expressions and gestures

Quick and easy operation

Rapid back-end web operations supported with simple, one-touch video generation following the input of broadcasting content. Produce professional broadcast-quality video fast even with no prior experience.

Smooth, natural-sounding speech

Two modes supported: text-driven and voice-driven. Pre-configured with numerous high-quality tones, the product supports pace and volume adjustment, text audition, and polyphonic pronunciation modification.