In a groundbreaking move, voice cloning startup ElevenLabs has introduced a new tool that allows users to generate custom sound effects through simple text prompts. As reported by TechCrunch’s Ivan Mehta, this innovative technology is set to revolutionize the way content creators, filmmakers, and audio enthusiasts approach sound design.
The tool, which is now available to all users, enables the generation of a wide range of sound effects, from the crashing of waves to the revving of a racing car engine. Users can also prompt the system to create instrumental musical clips, including guitar loops, jazz saxophone solos, and techno music.
According to the TechCrunch article, ElevenLabs has leveraged Shutterstock’s audio library, which contains licensed tracks, to train its model. This approach allows the tool to produce high-quality, realistic sound effects that can be seamlessly integrated into various creative projects.
While the free tier of the service offers 10,000 character generations per month, users will need to attribute the generated sounds to “elevenlabs.io” when publishing content that includes them. The company has also implemented safeguards to prevent the generation of content that violates its Prohibited Content and Uses Policy.
As the article notes, ElevenLabs is entering a crowded market, with several other companies and startups working on AI-powered sound generation tools, including Stability AI-backed Harmonai, Google’s MusicLM, OpenAI’s Jukebox, and Meta’s AudioCraft model. However, the unique capabilities and user-friendly interface of ElevenLabs’ offering may give it a competitive edge in the rapidly evolving world of generative audio technology.