Autotone – A vocal pitch correction web application, like Autotune | Hacker News Reader

Autotone – A vocal pitch correction web application, like Autotune

github.com

113 pointseviledamame17 comments

The demo gets stuck in "Loading CREPE model" state. The console shows:

    Uncaught (in promise) DOMException: The object can not be found here.

This is in a recent Firefox.

Works for me in FF 109.0b9 (64-bit) as soon as I allow access to the microphone.

I wonder if this could be used to remove upspeak and other indecisive or passive-aggressive tones.

I hope so?

this is really cool. by the looks of it, i'm going to need more than a vocoder to fix my voice.

This is fun! I wish it provided a way to save the audio too, but i see that's on the roadmap.

Practically, can this be used for real-time pitch shifting of an octave or two?

Since you identify an instrument or voice by its formants (which are more or less at a fixed frequency), it's unlikely to yield good results over such a large range.

I disagree. Sure, a naive approach wouldn't work (shift everything), but everyone's voice covers multiple octaves, so I'm sure plenty of people already know what changes need to happen if you sing in C2 but want to transpose it to C4, etc.

Of course there's some knowledge about that, but the approach in the link identifies the pitch by an NN (this step is not relevant to the current discussion) and then applies an FFT based method for pitch shifting that doesn't take any of it into account. So it'll shift formants as well, making voices and instruments change their character substantially.

Oh, yeah, that specific approach wouldn't work. It wasn't obvious to me if you were being specific about the article's approach or not.

Yes, that should be possible, the pitch shifting is very fast. I would expect the audio to sound pretty funky if you shift beyond one octave though

This is cool. Loved it. But the quality is kind of abysmal.

This may be because your sample rate was not a multiple of 16000. If that's the case, a low-quality, linear resampling is applied to the input audio to make it compatible with the pitch detection model. This resampling function should be improved.

I just pushed a change that will attempt to set your sample rate to 48000 now which may improve your quality. Additionally, your sample rate will now log out in the console.

no demo?

First link in the description: https://alexcrist.github.io/autotone/

I meant that I'm looking for some ready examples. Currently I have to connect a microphone and test it myself, which I'm not keen on doing

Reply on news.ycombinator.com