Elevenlabs Launches New SoundEffect Tool
TapTechNews June 2nd news, Elevenlabs has previously launched tools that use artificial intelligence to generate human voices and music, and now they have gone a step further by introducing a tool that can create sound effects for podcasts, movies or games.
The new tool of elevenlabs, named SoundEffects, can generate sound effects up to 22 seconds long based on the text description provided by users and can be used in conjunction with the company's original voice and music platform. After each use of SoundEffects, users can get at least four downloadable audio clips to choose from.
Elevenlabs has collaborated with the stock material platform Shutterstock and trained a generative model using its vast audio stock library. It is known that the content authorization objects of Shutterstock cover many well-known artificial intelligence companies such as OpenAI, Meta, and Google.
TapTechNews noted that SoundEffects offers both free and paid versions. The sound effects generated by paid users can be used for commercial purposes, while free users need to mark the source elevenlabs.io in the title. Elevenlabs has a limit on the number of characters in the user input text description, and free users have a quota of 10,000 characters per month. In SoundEffects, if the user sets the length of the audio clip by themselves, 40 characters will be consumed per second; if the default audio length is used, 200 characters will be consumed for each generation of sound effects.
Currently, there are already sound effect stock libraries in the market for creators, filmmakers, and game developers to use. However, the prices of these stock libraries may be relatively expensive, and it is sometimes difficult to find the exact sound effect that meets the needs. Elevenlabs stated in their blog that SoundEffects aims to generate rich and realistic sound effects quickly, cost-effectively, and on a large scale.
In addition to elevenlabs, other artificial intelligence developers are also actively researching and developing sound effect generators. StabilityAI released StableAudio last year, which can generate music and sound effect clips; while Meta's AudioCraft model can generate natural environment sound effects such as wind or traffic noise.