Live data from Hacker News

Lyebird: Clone Your Voice

descript.com

31–40 of 51 posts

Re: Lyebird: Clone Your Voice

#32

I have not yet had any serious use cases with this tech, but I've enjoyed playing around with it and I love its possibilities. (A while back, as an experiment, I recorded samples with a variety of silly character voices and fake accents; when the end result merged them into one, it sounded hilarious.)

Voice acting for ... games, audiobooks, etc?

Re: Lyebird: Clone Your Voice

#33

Earlier quoted context omitted.

Robocalling, with some interactivity. "Hello! This is Camp Ayne running for city council. How are your kids Doris and Eugene?"

That's going to be completely indistinguishable from phishing. How would you protect yourself from that?

Lenny will tie them up.

Re: Lyebird: Clone Your Voice

#34
I signed up for Descript and did the Overdub training a few weeks ago. It's impressive, albeit not a perfect match for my actual voice. You train the voice by reading 30 minutes of Wizard of Oz using a high quality microphone. I used a Yeti in a closet at my house. I do plan to record the additional hour of supplemental reading which might help make it more authentic.

(Side note - I didn't know Dorothy's shoes were actual silver in the book)

My use case for Overdub is to quickly correct errors in recorded demo/how-to screencast videos for my startup without having to do redo the audio.

Here's a sample of the Overdub output vs. my actual recorded voice if you're curious: https://web.descript.com/084a416c-57d4-4df8-980b-24e0df82532...

Re: Lyebird: Clone Your Voice

#35
Shoutout to Andrew Mason - I'm glad to see Detour/Descript continue on in some way. The guys that were building this back in the day were pretty sharp. Shoutout Ulf, Steve, DJW, Levi

Re: Lyebird: Clone Your Voice

#37
post #14

Show HN: I made https://vo.codes as a side project to democratize text to speech. It's got lots of celebrities, politicians, cartoon characters, and tech figures (Paul Graham, Sam Altman, Mark Zuckerberg, et al) Kids on YouTube found it and are making incredible music videos with it. Homer Simpson and SpongeBob cover Money Machine: https://youtu.be/iBpqJF5LXX4 SpongeBob covers WAP (NSFW!) : https://youtu.be/dSgd4PoQo…

text2speech and speech2speech seem like very different problems no? Especially when so much of someone's voice identity is based on speech patterns, contextual inflection, rhythm/cadence, how would realtime work? Just wondering if you are thinking about realtime as in Awesome progress by the way, would totally follow along more closely on this project through an eng diary or mailing list.

Re: Lyebird: Clone Your Voice

#38
post #2

Before Lyrebird was bought by Descript, this was a simple API endpoint. You could generate short MP3's of your digital voice reading any text of your choosing, for free. I used it extensively in one of my projects, only to find everything broken after leaving it alone for a few months. All of that to say, are there any alternatives out there HN knows of? This isn't an attack on Descript, either. The Lyrebird purchase…

Zohaib and I can always be found on these threads :)

The two main non Google/Amazon competitors are https://www.resemble.ai/ and https://replicastudios.com/

Re: Lyebird: Clone Your Voice

#39

I signed up for Descript and did the Overdub training a few weeks ago. It's impressive, albeit not a perfect match for my actual voice. You train the voice by reading 30 minutes of Wizard of Oz using a high quality microphone. I used a Yeti in a closet at my house. I do plan to record the additional hour of supplemental reading which might help make it more authentic. (Side note - I didn't know Dorothy's shoes were a…

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.

Re: Lyebird: Clone Your Voice

#40

I signed up for Descript and did the Overdub training a few weeks ago. It's impressive, albeit not a perfect match for my actual voice. You train the voice by reading 30 minutes of Wizard of Oz using a high quality microphone. I used a Yeti in a closet at my house. I do plan to record the additional hour of supplemental reading which might help make it more authentic. (Side note - I didn't know Dorothy's shoes were a…

Thanks for the sample. There's a flatness to the audio in recreation, but the major difference is lack of inflection. I imagine the latter might be tunable in a future incarnation.
Post reply on HN