> Voice replication: Recreate consistent vocal profiles from just a 30-second audio sample of your voice or a voice you have the rights to use, backed by built-in consent verification, SynthID watermarking, and C2PA credentials to protect both developers and their vocal talent.
I guess voice cloning is widely enough available now from other providers that Google are no longer hesitant to ship it.
Yesterday night I was doing a project with QwenTTS 1.7B.
After some debugging, making a clean dataset with clean recordings, and experimenting with a good fine tune recipe (much props to the new GPT models yesterday being cheaper).
I was able to make a robo-me that sounds absurdly good, family was shocked, all in a matter of a few hours.
so one of my interests is reducing the payload size for video games
the vast majority of the image sizes have been audio recordings, and its been that way in different qualities for the last two decades. this is still the case as more varied and comprehensive audio is pursued by studios at unfathomable expense and still failing to cross a bar of realism
good voice models are just a few gigabytes in comparison and can supplant all of that, and be run locally at this point. Future ubiquitous hardware configurations in consumer devices will make inference dedicated and computationally cheaper and faster
although AAA studios are hamstrung and will be deeply unpopular if they stopped booking voice actors
everyone else who would have never had the capital for voice actors will just use this and have richer experiences until they themselves are AAA studios from the market buying their rich experiences
this will vastly supplant the assumed and uninspired “tricking humans” use case from that video. once it crosses a threshold of ease, the applications will expand
simonw · · focus · HN ↗
I guess voice cloning is widely enough available now from other providers that Google are no longer hesitant to ship it.
kingstnap · · focus · HN ↗
After some debugging, making a clean dataset with clean recordings, and experimenting with a good fine tune recipe (much props to the new GPT models yesterday being cheaper).
I was able to make a robo-me that sounds absurdly good, family was shocked, all in a matter of a few hours.
So yeah the cat is out of the bag for sure.
yieldcrv · · focus · HN ↗
spuz · · focus · HN ↗
<a href="https://youtu.be/M-IVVJkZnuo?t=236" rel="nofollow">https://youtu.be/M-IVVJkZnuo?t=236
yieldcrv · · focus · HN ↗
so one of my interests is reducing the payload size for video games
the vast majority of the image sizes have been audio recordings, and its been that way in different qualities for the last two decades. this is still the case as more varied and comprehensive audio is pursued by studios at unfathomable expense and still failing to cross a bar of realism
good voice models are just a few gigabytes in comparison and can supplant all of that, and be run locally at this point. Future ubiquitous hardware configurations in consumer devices will make inference dedicated and computationally cheaper and faster
although AAA studios are hamstrung and will be deeply unpopular if they stopped booking voice actors
everyone else who would have never had the capital for voice actors will just use this and have richer experiences until they themselves are AAA studios from the market buying their rich experiences
this will vastly supplant the assumed and uninspired “tricking humans” use case from that video. once it crosses a threshold of ease, the applications will expand
peddling-brink · · focus · HN ↗
No que por los dos?
Don’t worry, we will be able to destroy careers and scam people at the same time. We don’t have to pick and choose!
yieldcrv · · focus · HN ↗
but let’s not pretend solo developers were ever going to have a voice actor suite and hire that talent en masse
the transactions were never going to happen
and now the outcome will be better than the studios that are making those transactions
peddling-brink · · focus · HN ↗
But I think you’re dancing on the grave of an entire industry, and every person that’s going to lose their life savings due to this.
yieldcrv · · focus · HN ↗
the market doesn’t want 15 year lead times and overly expensive and delayed games that don't experiment on anything
every friction plaguing the industry is solved by distributed indie developers being able to make richer experiences faster and cheaper