---
title: "Meta introduces a new AI model which can create video with sound"
publisher: "Stockmark.IT"
author: "Stockmark.IT Website"
published: "2024-10-07T04:27:01+00:00"
modified: "2024-10-07T04:27:01+00:00"
date: 2024-10-07
canonical: "https://stockmark.it/meta-introduces-a-new-ai-model-which-can-create-video-with-sound/"
category: "AI"
categories: ["AI", "Artificial intelligence"]
image: "https://i0.wp.com/stockmark.it/wp-content/uploads/2023/01/meta-sm-5.jpg?fit=480%2C270&quality=89&ssl=1"
format: "news"
language: "en-GB"
---

# Meta introduces a new AI model which can create video with sound

**Published:** October 7, 2024
**Author:** Stockmark.IT Website
**Categories:** AI, Artificial intelligence
**Featured image:** ![A 3D icon featuring the blue Meta logo on a white, rounded square background is shown against a purple gradient backdrop. @ stockmark.it](https://i0.wp.com/stockmark.it/wp-content/uploads/2023/01/meta-sm-5.jpg?fit=480%2C270&quality=89&ssl=1)

---

Meta (the owner of Facebook and Instagram) announced on Friday that it had developed a new artificial-intelligence model called Movie Gen, which can create realistic audio and video clips in response user prompts. It claimed it could rival tools from leading media creation startups like OpenAI or ElevenLabs.

Meta provided samples of Movie Gen’s work, including videos of animals surfing and swimming as well as clips that used real people’s photos to show them doing actions such as painting on canvas.

Meta stated in a blogpost that Movie Gen can also generate background music and audio effects synced with the content of videos. The model can be used to edit videos already created by users.

In one video, Meta used the tool to insert pompoms in the hands of an individual running in the desert. In another, it transformed a parking area where a skateboarder was skating from dry land into a puddle.

Meta stated that Movie Gen videos can last up to 16 second, and audio up to 45 seconds. Meta shared blind test data that showed the model performed well compared to offerings from startups such as Runway, OpenAI ElevenLabs, and Kling.

Microsoft-backed OpenAI first demonstrated in February how and its product Sora can create feature film-like video in response to text instructions.

The entertainment industry is eager to embrace such tools in order to improve and speed up filmmaking. However, others are concerned about systems that seem to be trained to copyright works with no permission.

The lawmakers have also expressed concern about the use of AI-generated fakes or deepfakes in election around the globe, including the US, Pakistan and India.

Meta spokespersons said that the company would not release Movie Gen to developers for free use, as it did with its Llama large-language models. They added that the company considers each model’s risks separately. They declined to comment specifically on Meta’s assessment of Movie Gen.

Meta, instead, said it was working directly with entertainment and other content creators to use Movie Gen, and would integrate it into Meta’s own products by next year.

According to a blogpost by Meta and a paper on the tool, the company built Movie Gen using a mixture of publicly-available and licensed datasets.

OpenAI met with Hollywood executives to discuss potential partnerships for Sora this year, but no deal has yet been announced. In May, Scarlett Johansson claimed that ChatGPT had imitated her voice for its chatbot without her permission.

In September, Lions Gate Entertainment (the company behind The Hunger Games, Twilight and other films) announced that it would give Runway, an AI startup, access to its entire film and TV library in order to train a model. The studio and its filmmakers can then use the model as a tool to enhance their work, according to the statement.

---

**Original URL:** https://stockmark.it/meta-introduces-a-new-ai-model-which-can-create-video-with-sound/
*Created by [WP Markdown Endpoint](https://wpmarkdownendpoint.com/)*