Save now
off all Envato Elements plans this Cyber Sale.
Get in quick!

We independently review everything we recommend. When you buy through our links, we may earn a commission.

ElevenLabs releases AI-powered text-to-SFX in partnership with Shutterstock

By Matic Broz
Hero image of ElevenLabs logo on a purple background

ElevenLabs, the company known for revolutionizing AI voices with its emotive, human-like Text to Speech platform, has announced on X (formerly Twitter) its latest innovation: Text to Sound Effects.

This new AI audio model, available now for all users, can generate a wide variety of sounds, including sound effects, short instrumental tracks, soundscapes, and character voices, all from a simple text prompt.

The Text to Sound Effects tool aims to empower creators across various industries, such as film and television studios, video game developers, and social media content creators, by providing them with the means to generate rich and immersive soundscapes quickly, affordably, and at scale.

ElevenLabs has showcased the capabilities of this new model through a video demonstration, where all the sounds featured were generated by their AI technology. Here are a few examples:

To bring Text to Sound Effects to life, ElevenLabs partnered with Shutterstock, a leading global creative platform that connects brands and businesses with high-quality, ethically-sourced content. By leveraging Shutterstock’s extensive and diverse audio library of licensed tracks, ElevenLabs was able to fine-tune its model, resulting in a versatile and powerful tool for modern creators.

Aimee Egan, Chief Enterprise Officer at Shutterstock, expressed enthusiasm about the partnership, stating, “We’re excited to be partnering with ElevenLabs to fuel yet another significant innovation in AI, Text to Sound Effects, with our ethically-sourced data. The combined power of our rich and immersive library of tracks and this cutting-edge audio technology has enabled the creation of a true market first. We’re thrilled by the positive feedback from the early access community and look forward to seeing the wide array of projects they will create.”

Using Text to Sound Effects is a straightforward process. Users simply need to log in, navigate to the Sound Effects section, describe the sound they need, and click generate. They can then review the generated samples and download the best results for their projects.

The following is a 2-second SFX I created with the prompt “Birds chirping in the forest after rain”. It’s eerily realistic, though still distinguishable from the real sound (for now).

ElevenLabs’ Text to Sound Effects marks another significant step forward in the company’s mission to equip creators with all the audio tools they need to produce high-quality content. With this new AI audio model, creators can now generate not only realistic, emotive voiceovers but also a vast array of sound effects, instrumental tracks, and soundscapes, all with the power of AI and a simple text prompt.

Posted in:

Meet your guide

matic broz
Matic Broz

Matic Broz is stock media licensing expert and a photographer. He promotes proper and responsible licensing of stock photography, footage, and audio, and his writing has reached millions of creatives.