Coqui
AI
voice cloning
SHOW HN2022
How HN took it
15 positive, 34 neutral or asking, 6 mixed, 14 critical, out of 69 comments about the project. Thread score +0.03.
Performance: 7 for, 6 againstIdea: 5 for, 1 againstPrivacy: 0 for, 5 againstExecution: 0 for, 1 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive voice cloning quality and cross-language results
From 4 comments
This is incredibly impressive and does a great job of capturing my voice. Well done!
pcarolan on HNThis is very cool. I recorded myself in Portuguese -> Portuguese and got the same result. I also did Pt -> En and sounded like... me speaking English, though with some artifacts.…
bernardom on HNI am French and I did try it, recording my voice in English (I have a thick French accent to English speaking ears, ok for French ones). And the result back in French was kind of…
bengalister on HNThis is great, my wife actually thought it was me speaking for a moment when she first came in!
thejosh on HN
Fun and cool to try
From 2 comments
I speak Brazilian Portuguese natively. I chose to record my voice saying a specific sentence and to "translate" it to Brazilian Portuguese using the exact same sentence. I was…
SwiftyBug on HNYou spoke Portuguese into it and it just changed your accent? That's kinda cool.
actually_a_dog on HN
Objections
Voice sounds nothing like the user in many tests
From 4 comments
As someone who actually speaks two languages - gave it a voice sample in Polish, then used it to synthesize the voice in English - sounds absolutely nothing like me. Meh.
gambiting on HNI just tried it and it sounds nothing at all like me. shrug
carbonx on HNMy 26 second training input perhaps wasn't enough. The result sounded like someone else. Is the result some kind of merger of my voice and a native speaker's?
sxv on HNI spoke for about a minute in English, having no idea what is the ideal length for it to properly figure out my voice. The result sounded like someone else completely. There was…
perryizgr8 on HN
Privacy and voice-impersonation fraud risk
From 3 comments
I'm curious but a bit afraid to test it out. The idea of having a model of my voice out there that can say whatever is written in a text box is scary.
tambourine_man on HNGreat opportunity for criminals and state actors to take identity theft to the next level.
Ice_cream_suit on HNCool, it's impressive how much can it do with a short sample, although this seems like an easy way for end users to deep fake their friends / enemies saying something.
alonmln on HN
Requests
Static demo without needing your own voice
From 2 comments
Is there a static demo that I don't have to provide my own voice for?
bagels on HNWe did not provide such a demo in part to hinder nefarious uses of the technology.
kdavis on HN
Better accent handling and translation fidelity
From 2 comments
Interesting. I like the addition of music to make sure it's not just a raw voice sample. The output I get seems to be a mix of a native speaker and my voice, because my (thick)…
jeroenhd on HNIs it supposed to translate or just read with the target accent? For me, it's only reading the English input text with the target accent.
akeck on HN
Questions
How does the company plan to make money given open releases
From 1 comment
This is so cool! Thank you! How do y'all intend to profit (succeed as a startup) if you're releasing so much publicly? I'd love to see you guys succeed. Really great to see where…
echelon on HN
Is the model available offline and how heavy is it
From 2 comments
Can tools like this exist in offline mode only? Or do they require some high-power computers for the model?
rambojazz on HNis the model available?
momolo on HN
Alternatives named
End-to-end speech translation research from Google
From 1 comment
This is called end-to-end speech translation, and has been around since 2017. Here's an article from 2019:…
forgotmyoldacc on HN
Spleeter for removing background music
From 1 comment
You can probably run the output through Spleeter[1] and get rid of the background music very easily. Just throw more AI at the problem... It's very hard to curb intentional…
marcan_42 on HN