More
Comments0
Computer Vision

I tried adding audio in Dream Machine and Sora’s silence is deafening

By AI Observer
I tried adding audio in Dream Machine and Sora’s silence is deafening
(Image credit: Luma Labs)
The AI video makers like Sora, and others, are mostly lacking even a flawed AI audio creator that can go along with their visuals.

  • Luma Labs added a score for the AI videos created on its Dream Machine platform. The new feature adds audio to your video that is custom-generated based on a written prompt, or created by the AI. This could be chirping birds for a sunrise scene, a distant hum from a spaceship in your sci-fi animated, the chaotic clattering of a busy café, or whatever else you want to hear. The beta version of the new feature is available for free to all users. You’ll notice that after Dream Machine has generated a video, a new “Audio button” will appear along the row of buttons at the bottom. This button is next to the “Extend” or “Enhance” options. You can choose to let the AI select the sounds it thinks are best, or you can provide a text description of what you want. You can use it to create a nature scene, and hear a distant water fall, or to hear the AI’s process.

    Luma AI: Introducing Video to Sound – YouTube

    Watch On

    Sound Idea

    The update is important because AI-generated videos have always felt incomplete, despite their sometimes stunning visuals. It takes a lot of time and effort to add audio manually. Even OpenAI’s Sora, one of the most popular AI video programs, does not have audio yet.

    AI sound generation is not unique. There are many AI music producers, including full voice and song creators. Dream Machine is a standout because of the production that’s already been done within the platform. It’s not perfect, but it’s still a good start. You can tell by the way the motion and sounds don’t quite match this dog as it is swimming.

    When prompted correctly, the crackling fire and laughter from people around it sound pretty good.

    I wouldn’t trust Dream Machine to make sound without a prompt. The AI used the same clip of people around the fire with a blank audio cue and created something much spookier.

    Dream Machine 1.5 catches Sora, and other rival AI Video Makers napping.

  • OpenAI Sora launches officially to change AI Video – 5 Things You Need to Know
    • Sign up to receive breaking news, reviews and opinions, as well as top tech deals.

    Eric Hal Schwartz has been a freelance writer at TechRadar for more than 15 years. He has covered the intersection of technology and the world. He was the head writer of Voicebot.ai for five years and he was at the forefront of reporting on large language models and generative AI. Since then, he has become an expert in the products of generative AI, including OpenAI’s ChatGPT and Anthropic’s Claude. He also knows Google Gemini and all other synthetic media tools. His experience spans print, digital and broadcast media as well as live events. He’s now continuing to tell stories that people want to hear and need to know about the rapidly changing AI space and the impact it has on their lives. Eric is based out of New York City.

    More on artificial intelligence

    Most Popular (

    )
    www.aiobserver.co

    More from this stream

    Recomended