Again, in some not-so-surprising news, we already have some great examples of how different AI models can be combined to further push this AI-generated medium to the next level.

It didn’t take long, but less than a week after OpenAI stunned the world with demos of their new text-to-video model Sora, we have another player in the AI space showcasing how they can use their AI to add dynamic audio and sound effects to the Sora demo video.

Along with their audio showcase though, let’s look at ElevenLabs and what their AI technology can offer in terms of text-to-speech and voice-generation possibilities.


ElevenLabs AI Sound Effects

So, putting aside any prejudices against AI and its eventual takeover of the world, this audio showcase from ElevenLabs is quite impressive. It’s cool to see another AI model pick up where one model left off as the OpenAI demo video of Sora lacked any realized audio or sound effects.

Shared via X (aka Twitter), it looks like the ElevenLabs team took the opportunity to jump on the viral sensation of Sora’s demo to further demonstrate how their technology could eventually be used in conjunction with these larger (and longer) generative AI videos.

Check it out for yourself below.

What is ElevenLabs?

Billing itself as a voice and AI research and deployment company, ElevenLabs’ mission is to make content universally accessible in any language. And so far, besides this Sora audio demo, they’ve been focused on providing realistic, versatile, and contextually-aware AI audio with a focus on voices.

ElevenLabs currently offers the following speech synthesis and voicelab products on their site, including:

  • Text-to-speech
  • Speech-to-speech
  • Dubbing
  • Voice Cloning
  • Voice Library

And, in total, they offer hundreds of new and existing voices in 29 languages. However, as you can see in their demo, it does look like they’re trying to expand beyond just voice and into more holistic sound effects and other audio types.

The Future of AI Voice and Sound Effects

ElevenLabs isn’t the only player in the AI audio game, but they’re certainly one of the bigger and more established ones. And, for those tinkering with AI for video, their offering of AI-generated voices (either text-to-voice or voice-to-voice) are quite great options.

The future of AI voices is changing fast, so it doesn’t seem like a stretch that technology like this could be a built-in part of Adobe’s Creative Cloud and offered in apps like Premiere Pro (or DaVinci Resolve or Final Cut Pro for that matter) in the future.

Still, as this AI tech continues to speed up, it’s going to be hard (yet important, perhaps) to stay on top of what’s being offered and how you could use it for your projects.