05:47:30 <m-relay> <c​0mmando:hackliberty.org> like https://paste.hackliberty.org/
06:55:24 <m-relay> <m​onerobull:matrix.org> very good video on haveno https://www.youtube.com/watch?v=kHnPukvGT7E
15:20:32 <m-relay> <k​orgprivacy:matrix.org> 📰Missed Monerotopia Episode (#171)? Check out the Price, NEWS, GUEST Segment. 
15:20:32 <m-relay> <k​orgprivacy:matrix.org> Reports here! ⤵️
15:20:34 <m-relay> <k​orgprivacy:matrix.org> 📊Price Report:
15:20:36 <m-relay> <k​orgprivacy:matrix.org> Youtube: https://youtu.be/4vDoYxxv7ow
15:20:38 <m-relay> <k​orgprivacy:matrix.org> ODYSEE: https://odysee.com/@MoneroTalk:8/crypto-still-chopping-sideways-06-22-24:c
15:20:40 <m-relay> <k​orgprivacy:matrix.org> 📰News Segment:
15:20:42 <m-relay> <k​orgprivacy:matrix.org> Youtube: https://youtu.be/A2xfYLVXwsw
15:20:44 <m-relay> <k​orgprivacy:matrix.org> ODYSEE: https://odysee.com/@MoneroTalk:8/face-to-face-xmr-transactions%2C-signal:0
15:20:46 <m-relay> <k​orgprivacy:matrix.org> 👥GUEST Segment:
15:20:48 <m-relay> <k​orgprivacy:matrix.org> Youtube: https://youtu.be/GJdbwdsLDe8
15:20:50 <m-relay> <k​orgprivacy:matrix.org> ODYSEE: https://odysee.com/@MoneroTalk:8/live-from-monero-square-at-porcfest!-06:8
16:34:17 <m-relay> <p​epe86frog:matrix.org> I really like your services homie
17:24:32 <m-relay> <r​ottenwheel:kernal.eu> Anime? No thanks. Distorted, spooky, odd voice? No thanks. Hard pass.
21:04:07 <m-relay> <m​onerobull:monero.social> you can also clone the voice of manly men if you are more into that
21:06:08 <m-relay> <m​mxxx:monero.social> don't put ideas in his head...
21:33:26 <m-relay> <m​cneb10:envs.net> yeah good luck finding software that can anonymize your voice without making sound like garbage
21:34:47 <m-relay> <m​cneb10:envs.net> unless you can figure out how to use so-VITS-SVC
21:34:55 <m-relay> <m​cneb10:envs.net> im going to try that
21:46:03 <m-relay> <m​onerobull:matrix.org> literally the software i suggested
21:46:38 <m-relay> <m​onerobull:matrix.org> although i dont know if you can maybe reverse it by training a model for it
21:46:51 <m-relay> <m​cneb10:envs.net> thats why you train the model yourself
21:46:56 <m-relay> <m​cneb10:envs.net> im sure it can be reversed
21:47:06 <m-relay> <m​onerobull:matrix.org> as in, take the cloned voice & the gura model, somehow get the original audio back out
21:47:06 <m-relay> <m​cneb10:envs.net> unless you are the only person with the model
21:47:10 <m-relay> <m​cneb10:envs.net> even then it probably can be
21:47:38 <m-relay> <m​cneb10:envs.net> probably it would be best to use so-vits-svc + an extra layer to add distortion to the audio
21:47:42 <m-relay> <m​onerobull:matrix.org> yeah if you have the original model and nobody else has, i dont think it would be possible unless the process of training models themselves is reproducible
21:48:33 <m-relay> <m​cneb10:envs.net> yeah thats a bit of a stretch but we don't know what's out there
21:48:44 <m-relay> <m​cneb10:envs.net> training a model is also extremely time and energy consuming
21:49:04 <m-relay> <m​cneb10:envs.net> it took 1 day per epoch for me on my K80
21:49:09 <m-relay> <m​cneb10:envs.net> they told me you need ~2000 for the best quality
21:51:00 <m-relay> <m​cneb10:envs.net> https://www.media.mit.edu/projects/voice-anonymization/overview/
21:51:30 <m-relay> <m​cneb10:envs.net> its probably just easier to do voice -> whisper -> tts in real time but then it sounds awful
21:54:01 <m-relay> <u​deeyyyvvv:matrix.org> DEMO AND REVIEWS https://matrix.to/#/%23newwwwwcpp%3Amatrix.org
21:55:08 <m-relay> <r​ecanman:kernal.eu> plowsof:
21:57:37 <m-relay> <m​onerobull:matrix.org> better to rent gpu by the hour
21:57:53 <m-relay> <m​onerobull:matrix.org> spend a few dollars, probably cheaper than training on your own electricity
21:58:06 <m-relay> <m​cneb10:envs.net> definetly but its cool to self host it
21:58:29 <m-relay> <m​cneb10:envs.net> when i did it i modified a powersuply and spliced the cables to plug it in to the GPU so it would have its own power
21:58:34 <m-relay> <m​cneb10:envs.net> and it still overloaded the PSU