Another Text to Speech API • Hacker News Board

Re: Another Text to Speech API

#11

Post by vmatsiiako » Mon, Sep 25, 2023, 10:09 PM UTC

willsmith72 wrote: post #4

maybe it's just me but the play buttons take forever to become clickable

works well for me

Re: Another Text to Speech API

#12

Post by BeetleB » Mon, Sep 25, 2023, 10:10 PM UTC

Frankly, these don't sound any better than Google Cloud's TTS, and is orders of magnitude more expensive.

Re: Another Text to Speech API

#13

Post by willsmith72 » Mon, Sep 25, 2023, 10:13 PM UTC

vmatsiiako wrote: post #11

willsmith72 wrote: post #4

maybe it's just me but the play buttons take forever to become clickable

works well for me

seems fixed now

Re: Another Text to Speech API

#14

Post by splatzone » Mon, Sep 25, 2023, 10:15 PM UTC

Interesting but there’s a weird pause before the word ‘danced’ in each demo? Sounds unnatural

Re: Another Text to Speech API

#15

Post by airstrike » Mon, Sep 25, 2023, 10:19 PM UTC

pruthvishetty wrote: post #6

Which is the best one, so far? Eleven labs? OpenAI apparently has something in the works to (going by today's Spotify podcast updates).

I'm also curious. A review of what's state-of-the-art today would be a great idea for a blog post. Just don't post it on medium.com please

Re: Another Text to Speech API

#16

Post by airstrike » Mon, Sep 25, 2023, 10:19 PM UTC

fuddle wrote: post #7

"Ultrarealistic AI Voice Generator" - I initially read the title as "Unrealistic AI Voice Generator". I'd suggest adding a space to "Ultrarealistic".

I also read the same thing

Re: Another Text to Speech API

#17

Post by stavros » Mon, Sep 25, 2023, 10:32 PM UTC

fuddle wrote: post #7

"Ultrarealistic AI Voice Generator" - I initially read the title as "Unrealistic AI Voice Generator". I'd suggest adding a space to "Ultrarealistic".

A hyphen, please.

Re: Another Text to Speech API

#18

Post by smusamashah » Mon, Sep 25, 2023, 10:39 PM UTC

pruthvishetty wrote: post #6

Which is the best one, so far? Eleven labs? OpenAI apparently has something in the works to (going by today's Spotify podcast updates).

Google Soundstorm had the best demo so far. It takes few seconds of original audio and continues it with the same voices. Just hearing those examples you wont figure out where original finished and generated one started.

Re: Another Text to Speech API

#19

Post by akshayys » Mon, Sep 25, 2023, 10:54 PM UTC

Hey everyone - I'm the founder of Fluxon. Just saw that we were on HN today - sorry for the late replies.

The app you're using right now is essentially an alpha-version - even the website was only made this week. Sorry about the somewhat-broken experience so far.

I'll try to get back to everything here in the next couple hours but if I miss something / you have other questions, please ping me on akshay@fluxon.ai

Re: Another Text to Speech API

#20

Post by radicalriddler » Mon, Sep 25, 2023, 10:56 PM UTC

robga wrote: post #10

pruthvishetty wrote: post #6

Which is the best one, so far? Eleven labs? OpenAI apparently has something in the works to (going by today's Spotify podcast updates).

Still Azure Speech in my experience.

ElevenLabs is better quality wise, but it's vastly more expensive. Azure Speech hits a really good price:quality ratio.