We are excited to introduce the ElevenLabs Text to Sound Effects API. To showcase it - we've built the first Video to Sounds Effects app. This app is available for free online and fully open-source. Our Sound effects API model enables everyone to build with fully custom AI sound effects. It's charged at 100 characters per generation when using auto-generation or 25 characters per second generated when setting a duration. Follow our tutorial here to get started: https://elevenlabs.io/docs/api-r...

Amazing!

i need to try this very interesting project

This is cool stuff, as always, ElevenLabs dropping 🔥🔥

Congrats on launching the ElevenLabs! The ability to upload any video and enhance it with custom sound effects brings a new dimension to video production.

looks cool ! I though to have seen a Hugging face doing it but yours is way cooler !

Congratulations on the release~ I wonder if I can propose my ideas to the AI, or manage my own audio library, and the AI will generate audio according to prompts, video content, and my personal audio library?

Congrats on the launch! Are there any plans to add the library of available sound effects? Excited to try it out and see how it enhances video content creation!

I've been following your journey for a while, and the strides you've made in AI and sound technology are truly impressive! Congrats! The Video to Sound Effects tool is a game-changer for content creators, making it easier than ever to enhance videos with custom sound effects

Congratulations on the launch! Could you share more about how the AI handles nuanced sound effects to match specific actions and scenes in diverse video contexts?

Interesting idea! I just uploaded a product demo video, but it seems that there is only the sound of tapping the keyboard and there is no beat point either. Maybe it has not been well adapted for software demo. I want to know which type of video will have a relatively better effect?

Nice product, the audio is generated quickly. I don't know what principles he will use to generate the audio. Can he really understand the message or emotion that the video is purporting?

Lots of fun to build this with Austin and leverage our great models

I feel like I can improve my work efficiency even more now