autoencoders

Adrian from Cleanvoice here.

Before building Cleanvoice, I tried to use Descript for my podcasts.

1) It doesn't work well if you have a strong accent. As an non-native speaker, the transcription were quite bad, making the editing quite bad.

2) Cleanvoice works with multiple languages, descript doesn't.

3) Cleanvoice can remove stutters (not always, but it tries) and mouth sounds like lip smacking, teeth clicking. Descript can't. This is not a big deal for most, but since I stutter alot this was essential.

However, if none of these apply for you. There is no reason to change from Descript.

Thank you for the suggestion and your impression. I agree, a better example would highlight it better.

Thank you for the suggestion. EDL/ADL is definitely on the list.

True. You don't even need a full CAP. Just some channels in the visual cortex. (With more advanced AI) So you would just need to hear a headband or one of those EEG which look more elegant.

The edit on the page is not the best. I agree!. Mainly, if your recording is unnatural (like that one) the edit is also unnatural. However, the tool works better in an interview podcast. I would strongly recommend to just upload a sample, and you would see a big difference.

Regarding if ML would be indistinguishable from humanly edit. Hard to tell. I think it will be like self-driving cars in the future. 98% edits good 2% bad edits.

It should be ok, since I use strictly essential cookies, which don't require consent. (But users need to be informed)

Or do I misunderstand the law?

[1] Strictly necessary cookies — These cookies are essential for you to browse the website and use its features, such as accessing secure areas of the site. Cookies that allow web shops to hold your items in your cart while you are shopping online are an example of strictly necessary cookies. These cookies will generally be first-party session cookies. While it is not required to obtain consent for these cookies, what they do and why they are necessary should be explained to the user.

[1] - https://gdpr.eu/cookies/

I appreciate it! If you have any issues or need help, feel free to reach out. (You can use the chat in the app.)

I agree, as if they don't breathe!

This is not the case with my app. I keep the edits longer than shorter, since I also find that unlistenable.

For now, Descript would be the best option. You can still make it work with the integrations, but it is a lot of effort.

That will change in Q2, when I add support for video.

Hallo Mike, freut mich dich kennenzulernen!

I trained my own models. No OpenAI/Google API.

Liebe Grüße, Adrian

Hey Justin! Love your podcast.

1) API Access will come end of Q1.

2) In the next 6 months, No. However, Auphonic would be a good fit for you.

Ups! Thank you for point it that out. I'll check it.

ADL Support is also around Q2, so you could just import it in your audio/video editor without issue. Thank you point out. I'll put Integrations on the homepage as well.

Wow! Thank you so much! You are right, I need to get ASAP a copywriter.

I'm curious why the Subscription + Onetime Credit is bad. But I agree it is confusing.

My understanding is that not every customer wants or needs a subscription, since they upload podcasts irregularly.

This business model is seen in other AI products:

https://www.remove.bg/pricing https://auphonic.com/pricing

I am very grateful, you took the time to help out. Really appreciate it!

Yes, the idea is to bring also prepaid credits soon.

Auphonic and Cleanvoice go well together.

I guess the idea is to have your podcast edited by Cleanvoice and then the audio post-processing with Auphonic.

It would be a huge engineering endeavour, which I wouldn't be capable of doing. That said, things like background noise and some sounds can be removed. See Krisp.ai

Yes, that's exactly the case. As I previously commented, I used an terms generator, until I get a lawyer, which can write specifically what I do with the data.

I like your idea, makes sense.

My biggest fear is that without login, people will start abusing it in ways that I don't expect. Definitely considering it. Thanks you!

I agree. More and more AI applications are exploiting our data in negative ways.

I will get proper terms soon as possible. Especially, since now people have mentioned it.

ADL Support will come around Q2, so you can import it in lot of audio and video editors. For now, we have these export files which you mentioned.

Regarding Pricing, that's a good point. I will definitely consider it, thank you!

For video is quite tricky. One thing with Video is that you don't want to over edit the audio, since its then very hard to keep the video synced. That said for explainer video it should work ok, but for a Video Podcast it would be horrible. I have an idea how to deal with this, but this is not now available.

It's not ideal. See the comment talking about the terms. I have a meeting with a lawyer soon. But I guess is better than no terms.

I agree. The terms will be changed. I used an auto-generated Terms generator for now (termly.io)

I would like to rewrite it.

What I do is just keep your files on the server for a week. In case you have an issue, I will look into your file to fix your issue. And if you want, you can give consent for me to further improve the service. (Say you have an accent which the AI is bad and I can use your audio file to understand why it failed.)

I tried to use Descript for my podcast, but it has some issues.

1) It doesn't work well if you have a strong accent. As an non-native speaker, the transcription were quite bad, making the editing quite bad.

2) Cleanvoice works with multiple languages, descript doesn't.

3) Cleanvoice can remove stutters (not always, but it tries) and mouth sounds like lip smacking, teeth clicking. Descript can't. This is not a big deal for most, but since I stutter alot this was essential.

My approach is different from Descript. They use a transcription service, and then they edit the audio based on the text. I work directly on the phonetics level. Allowing me to have more control over audio.

Depending on the needs, either one is better. I guess you should try it for yourself and compare.

> Is the example in the page really made by the computer? Yes. >In my opinion the pauses in where the filler words were are slightly too long. Is it possible to configure this? I agree, however, if you use it in an interview. The edits sound better. In an unnatural setting, you get unnatural results.

Currently, there is no way to set it for now. But customization is planned for Q2 next year.

>Is it possible to keep some filler words? For now no, but keeping some filler sounds to keep it authentic is something which I plan.

The audio is edited in several phases. It uses different algorithms, but most of them are deep learning based. It is surely overengineered, but as a Data Scientist, ML is the most fun part for me.

Hey HN!

I like podcasting, but I hate editing them. I tend to stutter and have a lot of filler words in my podcast. That's why I created Cleanvoice, in order to spend less time editing them. Cleanvoice is an ML tool which removes filler words, mouth sounds, stuttering and dead air from your podcast. To use it, just upload your podcast - wait some minutes - download the cleaned audio.

It's still not perfect, but it's at a stage where I can blindly use it on every single one of my podcast.

I would love to hear your feedback!