Meta Releases Movie Gen: 30-Second Video with Synchronized Audio
In one sentence Meta's Movie Gen generates 30-second 1080p videos with synchronized audio from text, advancing joint video-audio generation and raising deepfake concerns.
Meta unveiled Movie Gen, and it's a big step forward for AI video. Unlike most video generators that produce silent clips, Movie Gen generates the audio alongside the video — music, sound effects, ambient noise — all synchronized to what's happening on screen. You describe a scene in text and get back up to 30 seconds of 1080p video with a matching soundtrack. It also does personal video editing: you give it a photo of yourself and describe what you want to happen, and it can insert you into generated scenes. This is research preview only — Meta isn't shipping it to consumers yet — but the demo quality is striking. The technology raises serious concerns about deepfakes and synthetic media, particularly the personal editing feature that can make it look like a real person did something they never did. It also marks a major step in joint video-audio generation, which had been solved separately by most other labs.
Companies
Meta
Tools
Movie Gen
Tags
Sources