213
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 03 Dec 2023
213 points (90.2% liked)
Technology
34973 readers
192 users here now
This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
founded 5 years ago
MODERATORS
Not so much an expert rather than just parroting what I saw, but according to a cursory search, and a Twitter community note I saw from a friend, the voice used by this project is Synthesizer V, which is actually a perfectly legitimate piece of software for using digital voices in music production. If you've heard of Vocaloid, or know about Hatsune Miku, SynthV is basically a competitor in that space.
Going back to the community note, the voice used is actually called Natalie, and apparently the TOS of SynthV does not allow use of its voices using a name that's different to what was given. So they essentially can't present the Natalie voice as Anna, which they are.
EDIT: I want to clarify that these voice synthesisers like SynthV and Vocaloid are usually based on the recording of someone who has consented to the use of their voice in that regard and has been paid for it. It's not like the current AI voice cloning trend going on.
Tweet + Community Note
Thank you, I was wondering about the voice synthesis and if it was part of the AI model they used.
No prob! These digital voices have been around for over a decade now, maybe more. Some of them use "AI" to improve the sound of the voice (i.e. support more languages than actually recorded, make it sound realistic) but not in the way that current AI voice trends are going.
I've used Synthesizer V Studio and the clip in the video definitely showed that's what they used.
It looks like they should be disclosing ALL the tools they used to make this. Probably part of the TOS of the other programs too.