One thing I’d like to see ElevenLabs work on improving is volume standardization and balance. Some of my voices are quieter or louder than others and volume can change across some generations.
Yep, had this problem in my projects. It's all downs to mixing settings to fine-tune the voice and avoid glitches but it still happening - speed can change rapidly and volume level can also jumps.
Absolutely love. You make it look so easy and your explanations are very clear and the video is clean and well done. Really appreciate this. I’ve been looking for some decent 11 labs tutorials. Things seem to have changed on the platform a lot and I am very confused. (not unusual.😂)
Could you make a video going into more detail about the steps here 7:08-7:18 PLEASE. You talk about exporting an AAF to Premiere Pro which looks like something that would save so much time for editors, but I can't seem to get it working like in the video since a lot of the steps in between seem to be edited out.
Thanks for this video. I am having issues with importing a script with time stamps and two speakers. It imports correctly but as soon as voices get generated the time stamps get messed up requiring lots of manual adjustments which defeats the purpose of importing with the time stamps. Any suggestions or work arounds?
Something isn't making sense. At just around 4 mins a click is copied to show the blender attachments being fitted. However the second one sounds completely different to the first. Can you explain why?
what format is it expecting for start_time and end_time in the .csv? I always get internal server error when I try to include times. Would it also be possible to just use start time and dynamic generation?
I have tried every .csv format listed and cannot load a single file to voice over studio beta. Is there some sort of trick to actually loading it? Very annoying that you make it look so easy and then when you try to do it, NOTHING.
Every time you generate text, it takes away characters from your account… So if there’s text you want to alter or just edit once you regenerate it it pulls all those characters from your monthly allotment of account. Very annoying
DON'T USE 11 LABS... Spent 11 months making an audio book. Only to have customer service tell me they canceled the voice I was using... Just before I finished. Cost me $1,100 and hundreds of hours of work. THIS IS MY WARNING TO THE WORLD... Don't use 11 Labs. Worst customer service on the planet.
Descript is better for making faceless videos with their text-based editing. This is too tedious if you have a lot of content to create. Add test-based editing, also add audiograms and you're good.
Your site makes it IMPOSSIBLE to contact staff via email or chat with issues. Yet your company has the audacity to charge fees for an app you CANNOT even contact support to ask how to SLOW down a voice for a more relaxed sound in the text to voice section???? Terrible! If I cannot slow down the voice then I CANNOT use this at all!
What is really stupid is that on your website even if I am just checking the voices available with the already provided story you have put there, I can't even go through all the voices to see if it's worth it to get a subscription. Seriously !!!! I am not putting in my own story or words just checking all the voices is not an option wow
You speed of talk and your knowledge of the use of the program does not help anybody like me that is not a geek. Where are the written instruction on completing at least one project. without a dozen of jumping around to every option available with the program. You speak really fast.
I wish they would add a dark mode to their website.
I wish they would finally add emotional control to the voices.
Yes please!
Try dark reader chrome extension. Works nicely on most sites that have good CSS. I use it. :)
Exactly 😢
Extentions
ha...ha...ha... We need emotion control so badly! [laugh] / [giggle] / [sigh] / [cry] shor codes or something would be so powerful
Yeah its crazy they still did not add that. One would think it would be a priority.
One thing I’d like to see ElevenLabs work on improving is volume standardization and balance. Some of my voices are quieter or louder than others and volume can change across some generations.
Yep, had this problem in my projects. It's all downs to mixing settings to fine-tune the voice and avoid glitches but it still happening - speed can change rapidly and volume level can also jumps.
Absolutely love. You make it look so easy and your explanations are very clear and the video is clean and well done. Really appreciate this. I’ve been looking for some decent 11 labs tutorials. Things seem to have changed on the platform a lot and I am very confused. (not unusual.😂)
Looking forward to Suno and Udio beating music from ElevenLabs... and if we could pick the singer from our already generated voices, even better.
I’m so excited about this! 🎉
Could you make a video going into more detail about the steps here 7:08-7:18 PLEASE. You talk about exporting an AAF to Premiere Pro which looks like something that would save so much time for editors, but I can't seem to get it working like in the video since a lot of the steps in between seem to be edited out.
Great tutorials. Do more of a solo podcast episode. Thanks for sharing.
I use this everyday. Thanks for the video!
Pretty amazing tech here, all articles and books online could be on Spotify now with VO studio
Unfortunately, that would cost waaaaay too much money.
@@kirill3795 some will sell for cheap, to make money like Walmart does "high volume"
Great work! INSANE!! This really blew my mind!!! Immagino già moltissime applicazioni concrete!
I'm waiting for the music generator
Thanks for this video. I am having issues with importing a script with time stamps and two speakers. It imports correctly but as soon as voices get generated the time stamps get messed up requiring lots of manual adjustments which defeats the purpose of importing with the time stamps. Any suggestions or work arounds?
Amazing stuff! Keep up the good work.
Something isn't making sense. At just around 4 mins a click is copied to show the blender attachments being fitted. However the second one sounds completely different to the first. Can you explain why?
It’s so cool. Would be interesting to see this with DeScript workflow.
Nice video 🙏🌹❤️🙏🌹❤️🙏
Nice information 🙏🙏🌹🙏
It's possible to change the voice and change some text from the audio too? To change for example the speech of a film
❤❤❤ Eleven Labs the best App with audio voice ❤❤❤
Agree, I've tested some of the most popular and really like how elevenlabs sounds. The best.
what format is it expecting for start_time and end_time in the .csv? I always get internal server error when I try to include times. Would it also be possible to just use start time and dynamic generation?
I have tried every .csv format listed and cannot load a single file to voice over studio beta. Is there some sort of trick to actually loading it? Very annoying that you make it look so easy and then when you try to do it, NOTHING.
Can't get this to work. Add a video, click create and nothing happens.
A faceless video that had your face in it. Nice :)!
That male VO is everywhere on the internet
Feature idea (please upvote): STS removing my accent but keeping my emotion 😅
Very interesting!
Is this available for the free membership?
Amazing !!!!
Every time you generate text, it takes away characters from your account… So if there’s text you want to alter or just edit once you regenerate it it pulls all those characters from your monthly allotment of account. Very annoying
Wait he works for ElevenLabs?
👍Nice👍
Impressive
Add dark mode please
DON'T USE 11 LABS...
Spent 11 months making an audio book. Only to have customer service tell me they canceled the voice I was using... Just before I finished.
Cost me $1,100 and hundreds of hours of work.
THIS IS MY WARNING TO THE WORLD... Don't use 11 Labs. Worst customer service on the planet.
This is wild
But what if Iike Mike's voice 🙂 and not the raspy male V/O (lol)
Do you have 1$ discount or it is over?
now its 3$ discount
Descript is better for making faceless videos with their text-based editing. This is too tedious if you have a lot of content to create. Add test-based editing, also add audiograms and you're good.
Scary stuff
Abi siz naptınız bu nedir ya!
You guys suck u guys disable my usage bc of unusual activity when all i did is use it like how it’s supposed to be
I can imagine people using this to make kids content.
Your site makes it IMPOSSIBLE to contact staff via email or chat with issues. Yet your company has the audacity to charge fees for an app you CANNOT even contact support to ask how to SLOW down a voice for a more relaxed sound in the text to voice section???? Terrible! If I cannot slow down the voice then I CANNOT use this at all!
It's not free
Good ! 😂
@@qntmstudios1214 what is good in it
What is really stupid is that on your website even if I am just checking the voices available with the already provided story you have put there, I can't even go through all the voices to see if it's worth it to get a subscription. Seriously !!!! I am not putting in my own story or words just checking all the voices is not an option wow
You speed of talk and your knowledge of the use of the program does not help anybody like me that is not a geek. Where are the written instruction on completing at least one project. without a dozen of jumping around to every option available with the program. You speak really fast.
Bad explanations and poor understanding for beginners, bad