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.

David Attenborough is now narrating my life

431 pointsby andygcookover 1 year ago

25 comments

dangover 1 year ago
Related: <a href="https:&#x2F;&#x2F;github.com&#x2F;cbh123&#x2F;narrator">https:&#x2F;&#x2F;github.com&#x2F;cbh123&#x2F;narrator</a>
iris2004over 1 year ago
It&#x27;s a neat demo. I don&#x27;t know how I feed about cloning the voice of a living person, even a &#x27;public&#x27; figure like a presenter. I wouldn&#x27;t be surprised if it eventually becomes illegal, although it&#x27;ll likely be as difficult to enforce as normal casual copyright infringement.
评论 #38281367 未加载
评论 #38283289 未加载
评论 #38281559 未加载
评论 #38283941 未加载
评论 #38284826 未加载
评论 #38284634 未加载
评论 #38284587 未加载
评论 #38283739 未加载
评论 #38282607 未加载
rcarmoover 1 year ago
I want this, but with Werner Herzog. It would be the only way to do justice to the existential angst that pervades some of my meetings.
评论 #38287149 未加载
评论 #38282244 未加载
评论 #38290808 未加载
评论 #38282873 未加载
评论 #38282282 未加载
OnlyMortalover 1 year ago
“… and here we have the common Twitter poster. Their attempt to gain favour with their peers and, therefore, popularity with potential mates falls foul once again.”<p>- Attenborough maybe.
kadomonyover 1 year ago
Given the Attenborough Lore channel for Warhammer received a cease and desist, you can bet that his legal team will be busy suing the shit out of people like this.
评论 #38281927 未加载
评论 #38283447 未加载
tptacekover 1 year ago
This is simultaneously impressive and pretty gross.
评论 #38282793 未加载
评论 #38281478 未加载
LightBug1over 1 year ago
Interesting ... and awful ... it sharpens how I feel about it knowing that the man is nearing the end of his life. This is absolutely not how I want to experience and remember the man.
hyperificover 1 year ago
This is nuts. I want a version of this where Emma Thompson narrates my life like Stranger than Fiction.
评论 #38282113 未加载
smlacyover 1 year ago
<a href="https:&#x2F;&#x2F;nitter.net&#x2F;charliebholtz&#x2F;status&#x2F;1724815159590293764" rel="nofollow noreferrer">https:&#x2F;&#x2F;nitter.net&#x2F;charliebholtz&#x2F;status&#x2F;1724815159590293764</a>
itissidover 1 year ago
Oh man what a time to be alive. The creativity is amazing. Bravo.
Dig1tover 1 year ago
This is astounding. This is the kind of demo that we could only dream of just five years ago, now some hacker dude on Twitter can just throw this kind of thing together. Seriously cool.
xwdvover 1 year ago
It’s exciting to imagine that we can soon enter the age where people will be able to voice their opinions in their own voice and choice of words, long after they are dead and gone from this physical world. Perhaps the first version of some digital afterlife.
评论 #38281809 未加载
评论 #38283021 未加载
评论 #38281854 未加载
评论 #38283704 未加载
floatrockover 1 year ago
Isn&#x27;t part of the actors&#x27; strike about maintaining rights on AI-reproductions of actor likeliness?<p>This is a brilliant and effective demo of why that&#x27;s important.
评论 #38284148 未加载
BlueTemplarover 1 year ago
Reminded me of the South Park guys (et al.) take on Deep Fakes from a few years ago, especialy the bit with Michael Caine :<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=9WfZuNceFDM">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=9WfZuNceFDM</a><p>(Of course they used a real fake voice for all of them.)
评论 #38284019 未加载
consumer451over 1 year ago
I have really enjoyed the new show Scavengers Reign. It does an amazing job of showing an alien planet&#x27;s biodiversity. I have fantasized about a cut of just the nature scenes with Attenborough narrating. It seems like this make an attempt at that.
divbzeroover 1 year ago
YouTube is developing revenue sharing for AI-generated music [1]. I wonder if they will extend revenue sharing to non-musical content like the narration in OP.<p>[1]: <a href="https:&#x2F;&#x2F;www.theverge.com&#x2F;2023&#x2F;8&#x2F;21&#x2F;23840026&#x2F;youtube-ai-music-copyright-monetization-universal" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.theverge.com&#x2F;2023&#x2F;8&#x2F;21&#x2F;23840026&#x2F;youtube-ai-music...</a>
oldshatterhandover 1 year ago
I need Werner Herzog to narrate my life!<p>&quot;Look in the eyez of this nerd. The intenzity of the ztupidity looking at back at you is juzt amazing.&quot;
wsintra2022over 1 year ago
Pretty cool, a couple of months back a friend asked me if I could get him a Carl Rogers audiobook, I forget which one. I told him sure and jokingly asked if he wanted David Attenborough reading it. He said yes. I had myself a challenge. Long story short, I was able to create an audio book for a friend, the voice was meh!
VikingCoderover 1 year ago
I think you shouldn&#x27;t be able to distribute code &#x2F; model like this without permission...<p>...but...<p>What if you distributed code that when I ran it, and plugged in each of the Blue Planet &#x2F; Planet Earth DVDs, it would learn how to do this, with a local model?
nextworddevover 1 year ago
Wonder how he’s deciding which frame to feed to judge.py, given it would be tremendously wasteful to call gpt4vision on every frame. Maybe there’s some logic to detect meaningful drifts?
评论 #38282934 未加载
评论 #38282963 未加载
fnordpigletover 1 year ago
This is the future I was promised.
atleastoptimalover 1 year ago
I tried making something like this but OpenAI restricts Vision API calls to 100 per day rn
throwawaaarrghover 1 year ago
Take my money
gumballindieover 1 year ago
Without consent, of course.
评论 #38285701 未加载
SpaceManNabsover 1 year ago
I think this is nasty to provide as a service to others because the voice didn&#x27;t consent. I don&#x27;t agree with others when also critiquing personal use. Personal use should be fair use as long as you aren&#x27;t stealing or mining a service to minimize some personal cost.<p>So is this a text to speech model while mimicking somebody&#x27;s voice? That is pretty cool.<p>One thing I don&#x27;t understand is how you get specific models for someone&#x27;s voice. Do you fine tune to that voice?<p>The issue of style transfer is not something I understand for audio. Anyone have example papers to read? I am familiar with MuLan, MusicLM, and MusicGen.
评论 #38283012 未加载