Show HN: A free online British accent generator for instant voice conversion (audioconvert.ai)
I've developed a simple AI-powered British accent generator. Enter or paste your text, select the voice that best fits your project's tone, and generate speech for free. It supports up to 500 characters and offers 8 distinct, lifelike voices. Everything runs entirely within your browser.
I'm primarily seeking feedback on output quality, user experience, and any technical improvements worth exploring.
18 comments
[ 3.4 ms ] story [ 37.3 ms ] thread"Nature Show Host": not David Attenborough, surprisingly
"Compelling Lady": nothing beats a Jet2 Holiday
"Upset Girl": this is more the voiceover that would be used on depressing animal charity adverts
"Magnetic Man": you can't fool me, that's an American
"Patient Man": patience gives you reverb. The word "British" is spoken with a very non-British accent.
Not to be all Henry Higgins, but these are all "placeless" accents and there are no regional accent options. I was looking forward to trying Computer Mancunian. But I can see why for marketing voiceover people want "global neutral British".
UX review: "failed to generate speech". Only the example phrases work.
HTZc3SNl.js:1 Failed to generate speech: Error: Invalid API response format at Z (HTZc3SNl.js:1:29240)
That might work, but not for selling to Brits because they expect some sort of a local accent. Universal/unlocalised voice does not sound natural or believable to them.
(Also struggled getting it working at all as others already noted.)
Awesome stuff.
Who uses this term? English, Welsh and Scottish accents sound nothing like each other!
In the late 1990s I had text-to-speech on my run-of-the-mill 100mhz Pentium running Windows 98, with 8MB RAM. I could select the voice too.
It was also good enough to read my high school reading assignment, which I recorded to cassette and then listened to on a long drive.
---
So, what's novel about this site? As a learning project, it's pretty cool! (And I hope you built some good skills and enjoyed yourself making it.) Otherwise, there isn't much difference from what we had 30 years ago on much simpler hardware.
I have seen speech synthesis entirely in the browser, e.g. https://github.com/diffusionstudio/vits-web
It works quite well but is a bit slow to start because you have to download the models each time.