kundan2510

Descript | Research Scientist/Research Engineer | Head of Applied AI | Remote | San Francisco, CA | Montreal, CA

We're building a cloud-based collaborative video editor and a screen recorder that transcribes and aligns your audio with text - letting you edit videos like a word doc. We have built and shipped cutting-edge AI speech technologies like voice cloning, one-click speech enhancement, etc. used by the world's top podcasters, influencers, and businesses including BBC, ESPN, Hubspot, Shopify and Washington Post.

We're a team of 125 with a proven founder, and have raised $100M from some of the world's best investors like OpenAI, Andreessen Horowitz, Redpoint Ventures and Spark Capital.

We're seeking exceptional researchers to join our team tackling unique, challenging, and useful problems in generative modeling, and advance the frontier of AI speech, audio, and video.

https://www.descript.com/careers#open-position

Descript | Research Scientist/Research Engineer | Head of Applied AI | Remote | San Francisco, CA | Montreal, CA

We're building a cloud-based collaborative video editor and a screen recorder that transcribes and aligns your audio with text - letting you edit videos like a word doc. We have built and shipped cutting-edge AI speech technologies like voice cloning, one-click speech enhancement, etc. used by the world's top podcasters, influencers, and businesses including BBC, ESPN, Hubspot, Shopify and Washington Post.

We're a team of 125 with a proven founder, and have raised $100M from some of the world's best investors like OpenAI, Andreessen Horowitz, Redpoint Ventures and Spark Capital.

We're seeking exceptional researchers to join our team tackling unique, challenging, and useful problems in generative modeling, and advance the frontier of AI speech, audio, and video.

How does it compare with the training data you submitted to create your overdub voice? Sometimes, the voice sounds different because of the recording conditions, room tone, etc. and overdub voice copies these environmental factors as well.

We just launched a bunch of built-in stock voices as well: this is how they sound: https://twitter.com/andrewmason/status/1303384858249494529?s...

All these voices have been created via our voice cloning pipeline. Something to note: the generated audio is 44.1kHz and super crisp, ready to be useful for voice-overs or editorial corrections. Let me know if you have any questions about the tech. (I am one of the lyrebird founders.)

Hey! Lyrebird founder here! The simple API endpoint is work in progress. Please fill this form to get an early access: https://descript.typeform.com/to/Phn5zATR

I am one of the creators of the technology behind it. Please shoot any questions you may have.

Don't miss the overdub demo: https://www.descript.com/overdub and the demo video: https://www.descript.com/

Lyrebird AI | Montreal, Canada | ONSITE | Permanent | Senior Software Engineer

We are creating a developer platform for creating apps on top of existing voice cloning technologt. We are looking for experienced developers to help us in this awesome journey. Send your cv to [email protected]. You can see our website at lyrebird.ai. Thanks.