notebookLM to create podcasts.. i've created a small python to separate the voices (it creates 2 files, male.mp3, female.mp3) that you can use to feed into the various "hedra" or other saas to create talking avatars. No more struggles to manually separate the voices! (of course the audio files contain the "silences" when the other character is not speaking, so they perfectly match)
How do you make your own video it is very good like when you screen record you give your own audio then how do you replace the your audio with AI audio
Hey there, thanks for the comment. It’s a lot of work but here are the steps: 1. Record the screen and your own voice. 2. Edit it a little bit just a rough cut. 3. Make a transcript then a caption of this edit with your voice. 4. Spellcheck the caption and export as a text file. 5. Use the “narrator text” in an AI Voice generator to create the voice 6. Import the voice back into editing software. 7. Edit it bit by bit so the screen records match the new voice. (this step is very time consuming) 8. And Optional for YT: Make again a caption of the new voice and spellcheck it. Alternative: You can use “audio to (synthetic) audio” but if you have an accent the accent will be in the generated voice which can sound strange. Hope you get an idea how to do it. 😊
@@moreaistuff keep it up bro thank you so much for replying me in so much detail you are great keep going your last video was very helpful how much total time it takes you to make one video on this channel
Great stuff.. i need clarity on the adding of two audio tracks in hygen. You mentioned loading both separated audio into hygen to start and then the single person per clip as the "script" audio, is that right?
Love the video and want to do it but as a beginner the way you explain or show how is hard for me to create it would be good if its slower and clearer in video.
I want to ask that supposed I make a video then a extract my voice and convert it into ai voice. This is process you follow. IF NOT Then give me link🔗 of tutorial videos
I use my voice only for the recording, then make a subtitle of it and then use this “narrator text” and let the AI Voice speak the text. Search for “how to ai narrator” and you will find tutorials.
Hey thanks for the comment. You can use tools to translate the audio and then follow the process in my video. Just google "translate audio to other language" and use a site you like. Hope that helps. Good luck. 😊
@@Kelvinapplegate “by this comment”, not “buy”: I know they sound the same but they’re not. Ask your kindergarten teacher to explain the difference. ;-)
@@toninotonnato7776 Speech to text did that. Also is that the way that you usually respond when someone attempts to make humor if so that's fine I'll leave you to your devices. Making sure grammar punctuation and words are spelled completely accurately in online Light-hearted conversations( or so I thought it was)are the least of my concern when they're really things I do in passing while I'm trying to get more important things accomplished. Again my fault though.
Kudos, one of the best PoC vodcast examples so far.
😮😢😂😅😊
notebookLM to create podcasts..
i've created a small python to separate the voices (it creates 2 files, male.mp3, female.mp3) that you can use to feed into the various "hedra" or other saas to create talking avatars. No more struggles to manually separate the voices!
(of course the audio files contain the "silences" when the other character is not speaking, so they perfectly match)
Thanks for the comment. Sounds good. Do you have a link so people can try it out.
i wish you could share it with us :)
@@GrandpaGraphic i published it on "buy me a coffee", look for user "goldensio" :D
Use Descript to separate the voices.
Wow..Another point
How??
I checked it. Google this "How to split audio files online descript" first result is the answer and a how to.
but how to export separately?
ElevenLabs and DeepGram will also do speaker segmentation.
😮😢😂😅😊
Speaker split seperates the voices for you
Dope video, AI is really crazy nowdays, and its just the begginning!!!
Definitely just started way more crazy things are coming. Thank you for the comment.
Amazing this is crazy
Descript has a feature to separate voices.
"Like my voice for example" is nuts!?!
Wow this is excellent
Good job
Thanks 😊
Wow awesome
Thank you for this!
Your welcome. 😊
Wow great video 😮
Thanks 😊
Wao it is great ❤
Thx☺
this went wild wahhhhh
Yea pretty crazy stuff.
Awesome
Thanks.
you did good
Thanks for your comment.
Great 👍
Thank you 👍
Wow
This is awesome
What about some of us that are novice in video editing. Any other way we can do this?
Hey thanks for the comment. It's pretty easy editing, you can do it in any free video editor aswell.
How do you make your own video it is very good like when you screen record you give your own audio then how do you replace the your audio with AI audio
Hey there, thanks for the comment.
It’s a lot of work but here are the steps:
1. Record the screen and your own voice.
2. Edit it a little bit just a rough cut.
3. Make a transcript then a caption of this edit with your voice.
4. Spellcheck the caption and export as a text file.
5. Use the “narrator text” in an AI Voice generator to create the voice
6. Import the voice back into editing software.
7. Edit it bit by bit so the screen records match the new voice.
(this step is very time consuming)
8. And Optional for YT: Make again a caption of the new voice and spellcheck it.
Alternative: You can use “audio to (synthetic) audio” but if you have an
accent the accent will be in the generated voice which can sound strange.
Hope you get an idea how to do it. 😊
@@moreaistuff keep it up bro thank you so much for replying me in so much detail you are great keep going your last video was very helpful how much total time it takes you to make one video on this channel
@@ytn2025 Not sure exactly maybe between 8-12 hours depends.
@@moreaistuff Great work dude. I had to subscribed and liked the video. Can you make make these steps (your voice to Ai voice) into a video?
Great stuff.. i need clarity on the adding of two audio tracks in hygen. You mentioned loading both separated audio into hygen to start and then the single person per clip as the "script" audio, is that right?
Right you upload on the left where it says "asset" and then it will show when u add the "script".
I love that
Thank you.
what is a video editor that u use?
I used Adobe Premiere Pro, but you can you use any editor you want. Davinci Capcut and so on.
Love the video and want to do it but as a beginner the way you explain or show how is hard for me to create it would be good if its slower and clearer in video.
You can slow down any TH-cam video click the cog below any video
Yea and you can watch it again. And once in the applications it's pretty easy to follow. Wish you good luck. 😊
What voice/tts model did you use to narrate this video?
It's the good old adam from elevenlabs.
@@moreaistuff And I though it was notebookLM
can I do it in Canva?
Maybe parts of it but not the whole thing.
How you voice created by ai
Thanks for the comment. The voice is created with elevenlabs.
I want to ask that supposed I make a video then a extract my voice and convert it into ai voice. This is process you follow.
IF NOT
Then give me link🔗 of tutorial videos
I use my voice only for the recording, then make a subtitle of it and then use this “narrator text” and let the AI Voice speak the text. Search for “how to ai narrator” and you will find tutorials.
I started another page with this method
nice.
How to make the same process in other language?. NotebookLM only make podcast in English.
Hey thanks for the comment. You can use tools to translate the audio and then follow the process in my video. Just google "translate audio to other language" and use a site you like. Hope that helps. Good luck. 😊
And portuguese from Brazil at least
Nice,
And I found out that is age restricted,
You have to be 20 above, so u have to change your age, thanks
Damn.
I hear that hosts voice far too often
I still like it ;)
By the way he talks and the basic jokes he does, I would bet the creator of this video is 13yo (with the synthetic voice of a 59yo from Louisiana 😂)
Buy this comment comment I would say it was you 😂😂😂 Silly 😅
Mabe he is. I ask him. 😉
@@Kelvinapplegate “by this comment”, not “buy”: I know they sound the same but they’re not. Ask your kindergarten teacher to explain the difference. ;-)
@@toninotonnato7776 Speech to text did that. Also is that the way that you usually respond when someone attempts to make humor if so that's fine I'll leave you to your devices. Making sure grammar punctuation and words are spelled completely accurately in online Light-hearted conversations( or so I thought it was)are the least of my concern when they're really things I do in passing while I'm trying to get more important things accomplished. Again my fault though.