TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: VoiceClonr attempts to reconstruct human voices

56 pointsby voiceclonralmost 10 years ago

12 comments

elmalaakalmost 10 years ago
Certainly it's still far from being able to deceive a human into thinking synthesized speech of any speaker saying anything is real, but it has definitely and clearly capture a certain quality to each of those voices. Really cool project and I'm sure it portends even more awesome work in the area.
cristianpascualmost 10 years ago
I am wondering, what exacly is holding back the technology? Why isn't it there yet?
评论 #9813912 未加载
chillingeffectalmost 10 years ago
I love that you&#x27;re shooting for a holy grail!<p>Aiming for lyrics is a much higher target than everyday text though, due to grammatical hints and the extra pitch and phrasing demands of lyrics. Your results might hit people harder on non-lyrical textual bodies.<p>Keep up the good work, I&#x27;d like to make something like this for musical instrument someday :)<p>P.s. have you ever heard of Douglas Hofstadters Letter Spirit project which synthesizes fonts from a subset? <a href="http:&#x2F;&#x2F;www.cogsci.indiana.edu&#x2F;farg&#x2F;mcgrawg&#x2F;fonts.gif" rel="nofollow">http:&#x2F;&#x2F;www.cogsci.indiana.edu&#x2F;farg&#x2F;mcgrawg&#x2F;fonts.gif</a>
slantyyzalmost 10 years ago
This is very cool.<p>Reminds me of this -- before Roger Ebert died, he tried to have his voice reconstructed by some company using audio from his TV show, etc., but alas, it was too difficult at the time, so he ended up using one of the Apple TTS voices instead.
评论 #9815265 未加载
评论 #9814052 未加载
Zikesalmost 10 years ago
I would pay a fair amount for a TTS engine that can accurately mimic GLaDOS&#x27;s voice.
评论 #9816447 未加载
评论 #9815134 未加载
评论 #9814670 未加载
ocdtrekkiealmost 10 years ago
I&#x27;m super excited about this.<p>One of my biggest peeves right now is that voices cost a ton of money, few are readily available otherwise, and a lot of the new stuff is cloud-dependent. (Which is a big turn-off to me.)<p>What are you looking to do with this?
评论 #9816127 未加载
secfirstmdalmost 10 years ago
There have been rumours of government capability to do this for some time. For example, to use false voice messages for Radar instructions to enemy fighters etc. Interesting to see it in the commercial space.
评论 #9815424 未加载
scottydeltaalmost 10 years ago
And I was hoping to find Morgan Freeman&#x27;s voice there already.
评论 #9813962 未加载
ocdtrekkiealmost 10 years ago
Request: Star Trek computer voice (Majel Barrett Roddenberry)<p>There&#x27;s hundreds of episodes containing it, including remastered audio in the HD versions of TNG.
fasoutoalmost 10 years ago
Very nice project, congratulations!<p>One suggestion: make the text-to-speech button bigger and centered (I missed it the first time).
评论 #9814259 未加载
acdalmost 10 years ago
Could a deep neural network clone the voice of a person given previous sound recordings of that person speaking?
评论 #9824333 未加载
SchizoDuckiealmost 10 years ago
They all just sound robotic to me.<p>Why even attempt to get things like imitating specific people&#x27;s voices to work when your speech isn&#x27;t even fluid and pronounced clearly to begin with?
评论 #9813849 未加载
评论 #9814506 未加载