boojumliussnark

Thank you again for diving in to this. It looks like speechify don't support Danish.

On Resemble AI, they have something like Elevenlabs:

For professional voice cloning through data upload, we require explicit, verifiable consent from the voice talent. This involves providing a clear audio consent statement along with the training data, so that we can confirm the identity. By uploading voice data, you're confirming that you have such consent, which should align with our guidelines. The consent recording must follow our template, e.g., "I acknowledge my recordings will be used by [Your Company] to create a synthetic voice by Resemble AI." For any questions regarding consent, please reach out to us.

I will try to contact them regarding my use, which is neither commercial, nor using "voice talent" exactly.

This project looks very cool, but at 300usd+ I think it is out my budget range for this project.

Was this with the "Instant voice clone"?

Looks very cool. I was unable to see anything regarding languages. Is it completely language independent somehow, or is it English only?

I can't find this. Where is it on the German page?

Thank you for the tips. As I see it currently, I expect the language to be the biggest hurdle. It doesn't appear like something I can add myself, even if I had the data for a model. So as far as I can tell it involves two currently more or less impossible steps: Get model data and teach language to model.

I did sign up for ElevenLabs, unfortunately they cannot allow me to clone a dead persons voice, as per their FAQ:

You may only clone your own voice or a voice you have the rights to clone. For added security, when creating a Professional Voice Clone we require users to complete a Voice Captcha mechanism by reading a text prompt within a specific time to confirm your voice matches the training samples you upload for training. If there’s a match, your request is sent for fine-tuning. If not, you’ll have to reach out via our help center to have your voice verified manually.

Now I'm sure it wouldn't be an issue to get the legal rights, but when I spoke to their support, they did not have any way to verify beyond the captcha.

Thanks for having a look. Yeah it's because of the paper. I dug into the source and the research they cited, and it sounded a lot like lactulose was pretty much ineffective at promoting any of the really beneficial bacteria. And the price for chemical grade Rhamnose is way beyond my budget, especially as, as far as I could tell, the dosage is pretty high, to get the benefits.

Yes, as I said - I do NOT mean lactobacillus rhamnosus.... Just read the message

To be clear - I do not mean lactobacillus rhamnosus.

Thanks again for looking at this!

The NTC meassures very low ohm, in circuit it's around 14 ohm.

The markings on the "receiver" board are: +27v, gnd, -27v and "mute".

I would like to try to do some "divide and conquer" debugging, as the total number of components is rather low. I would like to try to eliminate the different "blocks". Like I can connect it up, and measure the voltage after certain "stages". Maybe after the inrush current limiter? To my very limited understanding that should be right at the end of the AC block/stage? Maybe dividing the board into 3 or 4 stages like this I could start to narrow down the issue?

I am guessing the MOV is the component marked MOV on the board, its markings are: TVR 07471. Can I test this "in-circuit, or must I de-solder it to test it?

In-Circuit I measure around 470kohm