Hey ProductHunt, we're thrilled to share our new Voice Isolator model with you! As demonstrated in the video above, it's great at extracting crystal clear audio from any of your noisy videos! We think it fits right into your audio production toolkit and can't wait to hear what you think! For API access, we plan to launch that in a couple of weeks, and in case you missed it... we're also giving the leaf blower in the video away 😂 to the best examples of voice isolation that we see! (https://twitter.com/elevenlabsio...) Shoutout to @tim_von_kanel and our incredible research team for making this possible. Let us know what you think!

Any API?

Suuuper cool – I've tried different voice isolator models and this by far exceeds most of them! Congrats on the launch 🎉

Best video with our voice isolator wins the leaf blower!

I wish I could use API and integrate it into my app

Have you considered adapting this to hearing aid technology?

Tested it. Do you have to write a script for it to work? Or can you just upload a conversation in a busy cafe and mute out the background noise?

Love this project a lot. I record a lot of audio from time to time that has a lot of noise because my camera's mic isn't that good. So I really appreciate this product.

Omg, this is so cool!

🤯🤯

I had to try this! Yesterday, I was recording a demo when sirens 🚨 ruined the audio 😂 (I think the police chased me for using illegally bad mic!)

This sounds great - will be very helpful! Can't wait to try it out!

Does Voice Isolator support batch processing for multiple audio files at once? Also, any plans to integrate it with cloud storage services?

Can this tool automatically remove the irrelevant parts from a long meeting? For example, the silent moments at the beginning, filler words, empty pauses, background noise, and so on. It would be great if it could keep only the actual speaking parts.

That’s very cool 😎 🔥🔥

Congratulations on the successful launch of your impressive product! The demo is working well, and I believe it will meet its users' expectations. I'm curious about how the product selects its primary and background voices. Does it offer users the option to choose their preferred voices?

Another mind blowing feature by ElevenLabs. Congratulations!

Good product for sure! +

This Voice Isolator sounds amazing! Thanks for sharing this cool tool!

That demo video though! Hope you are wearing an ear plug my guy! This is when you know the product is damn good. Question, how does this work with an environment where the main speaker is quiet (and maybe farther away from their computer) and there are conversations in the background? How does the model recognize the main speaker voice? Does this only work with certain frequency of sound? I'm also curious how does this work for streaming audio since this could be something that's useful to improve speech to text? We work in an environment where we have lots of young students (potentially) in an open space, and we are thinking we could use this tech to enhance the audio. What would be the delay be like? Anyways, big props and congrats on the launch @ammaar and team!!