Seems good so far however I'm not impressed with each generation using character credits whether you are happy with the output or not. Surely you should only use them when downloading otherwise you'll blaze through your quota without achieving what you need for your project. Some generations have completely missed the context of the narration on some scripts I've been experimenting with.
@@brothernobodyALWAYS preview audio in PROJECT... THERE WILL BE A PLAY BUTTON HEADER.. USE MOUSE TO HOVER OVER A SENTENCE OF YOU WANT TO PREVIEW.. I found this the only way it works. Just open up a project and add text the canvas. GOOD LUCK!!!!
I just experienced the speech-to-speech. It’s outstanding! I hope it will be incorporated into Projects. Basically, allowing us to highlight sentences and record our tone and style right in the moment. Also, I agree with others that credits should be only subtracted once one submits their final draft. Without this, it’s almost the same cost as a human narrator.
I just want to say. I love you guys. I am very happy with the service and the emotive work you guys have done whereby the ai understand whispering, angry ect is just amazing!
It would be really nice if you could, highlight text and select an emotion... sad, mad, happy, melancholy, excited... etc. Already awesome, but would make the tool 100% more useful for this application! 🙏
I hired the creator plan with the purpose of creating audios of the drug leaflets for the company I work for, but my experience so far leads me to believe that I made a bad hire. In addition to having already spent almost 60% of my plan during testing and before converting the audios, after conversion and download the audios are coming with an American or Castilian accent, another male voice appears in the middle of the audio when I select a female voice (Matilda) and the platform does not recognize the language as Portuguese or offer a manual definition option.
Do you know that: can the ultra realistic voices such as Brian be used by API? I want to use API for voice pieces by which I want to merge these pieces for synchronization for the dubbing videos. Probably for now, there is no property of adding delays. I am trying this synchronization process over subtitles. I wish you could add "reading subtitle by caring the time numbers in the subtitle" by making a simple code such as "(pause until 00:00:03,488)" which can be assumed as the left side of any subtitle numbers.
Looks good but voice instability (volume drop) has been something that kept me from even experimenting. Hopefully that has been solved because otherwise this looks interesting.
i agree with below. Great program but pricing is impractical for large projects. It would be better to pay for down loads. many of the transcript translations have artifacts. but use credits satisfied or not. if that isn't fixed. then i guarantee someone will come along and fix it elsewhere. Maybe its available on the higher tier. hmm still not good if credits dissapear satisfied or not. Espec if higher tier is also gonna be for people with higher credit usage.
The timing couldn't be better, I just spent an hour going back and forth in an audio editor piecing bits of generations together. My use case is more for sales presentations rather than audiobooks. I want to use a single voice but switch between default presets for the same voice to make her sound more excited or serious.
@@MondayAbiola Every space and character is counted. This sentence: "I drove to the store" is counted as 22 characters, including the quotes, and used against your credits. Without spaces and quotes, the character count is 16. In a 3733-word document I created it had a total of 3717 spaces, and that's not even including the breaks between paragraphs, which, I believe, are also counted against your credits. We definitely get charged for non-speech related characters. After testing and finding the right voice, you will waste lots of credits. Other companies are probably going to introduce a better model soon based on speech-only credits and take a lot of business away from them, i predict.
The character limit in text is a joke. I'm waiting for Microsoft to create competition because it's just a gimmick aimed at gaining additional funds, pay pay pay...
It's not that great. Blows pronunciation, and charges you for corrections. No clue as to putting together the pieces of a project to make a single audio book. Notice that this video promises you a lot but in spite of highlighting piees that in no way connect to fulfilling actual tasks, it's not showing you how to do anything. I plan to finish in ElevenLabs, correct in Audacity, and switch to Bowker
I'm becoming really frustrated with not being able to regenerate just ONE SECTION. This is making my audio book take so much longer because there are no clear directives (or tutorials online) as to how to regenerate ONE sentence in a chapter. When I press regenerate the whole damn chapter regenerates and messes up a different section.
Eu usei 5 mil carateres e gerei a voz do Adam e não apareceu o botão de download e saiu da página. Eu fiquei chateado e escrevi tudo de novo e a mesma coisa aconteceu e perdi ao todo 10 mil caracteres. E fiquei sem postar minha matéria. Eu quero que me devolvam os 10 mil carateres que não baixei. A opção de download deveria aparecer assim que gerasse a voz e não obrigar as pessoas a ouvirem tudo. Eu faço tudo pelo celular
This website gets useless after a while. I use this thing for stop motions and it says my character limit has ended and it says I need to pay to get more. Please fix this
in the second month, they blocked all the voices and did not return the funds for the reason that they were allegedly not mine, only I installed them myself, twisted them so that it would be a female male or an old man’s voice, and as a result they took the money and derailed 1.5 months of my work.
This is a useless website, I created an account several times and each of them blocked me saying that you are using a VPN while I was not using any VPN.
It's not perfect. It still makes mistakes. If it mispronounces something in a paragraph or the flow is mismatched, it will fix it most of the time, not all the time and it will redo the whole paragraph, not just the one line, so it will cost you more. It's very easy to overspend correcting mistakes with this program even though for the most part it's great. Just be careful of the trap of constantly try to redo its errors. Turns into a money pit after that.
Seems good so far however I'm not impressed with each generation using character credits whether you are happy with the output or not. Surely you should only use them when downloading otherwise you'll blaze through your quota without achieving what you need for your project. Some generations have completely missed the context of the narration on some scripts I've been experimenting with.
Exactly. It wouldn't be hard for them to produce low quality/distorted playbacks so we can edit outputs before spending credits
Their pricing model makes the whole system too expensive to produce a full audiobook. Even paying a human $30 an hour is cheaper.
Please help, how do they count characters in eleven labs... With spaces or not?
@@brothernobodyALWAYS preview audio in PROJECT... THERE WILL BE A PLAY BUTTON HEADER.. USE MOUSE TO HOVER OVER A SENTENCE OF YOU WANT TO PREVIEW..
I found this the only way it works. Just open up a project and add text the canvas. GOOD LUCK!!!!
@@MondayAbiolayes spaces count. Even space between each paragraph
Mind-blown every time guys. The multi-voice function is well-received.
I just experienced the speech-to-speech. It’s outstanding! I hope it will be incorporated into Projects. Basically, allowing us to highlight sentences and record our tone and style right in the moment.
Also, I agree with others that credits should be only subtracted once one submits their final draft. Without this, it’s almost the same cost as a human narrator.
I just want to say. I love you guys. I am very happy with the service and the emotive work you guys have done whereby the ai understand whispering, angry ect is just amazing!
It would be really nice if you could, highlight text and select an emotion... sad, mad, happy, melancholy, excited... etc. Already awesome, but would make the tool 100% more useful for this application! 🙏
I hired the creator plan with the purpose of creating audios of the drug leaflets for the company I work for, but my experience so far leads me to believe that I made a bad hire.
In addition to having already spent almost 60% of my plan during testing and before converting the audios, after conversion and download the audios are coming with an American or Castilian accent, another male voice appears in the middle of the audio when I select a female voice (Matilda) and the platform does not recognize the language as Portuguese or offer a manual definition option.
It has been a great experience working with Projects this month.
Do you know that: can the ultra realistic voices such as Brian be used by API? I want to use API for voice pieces by which I want to merge these pieces for synchronization for the dubbing videos. Probably for now, there is no property of adding delays. I am trying this synchronization process over subtitles. I wish you could add "reading subtitle by caring the time numbers in the subtitle" by making a simple code such as "(pause until 00:00:03,488)" which can be assumed as the left side of any subtitle numbers.
Yes!
Breaks of up to 3 seconds are being added soon as per their update post on discord
Looks good but voice instability (volume drop) has been something that kept me from even experimenting. Hopefully that has been solved because otherwise this looks interesting.
The Best 💯💖
i agree with below. Great program but pricing is impractical for large projects. It would be better to pay for down loads. many of the transcript translations have artifacts. but use credits satisfied or not. if that isn't fixed. then i guarantee someone will come along and fix it elsewhere. Maybe its available on the higher tier. hmm still not good if credits dissapear satisfied or not. Espec if higher tier is also gonna be for people with higher credit usage.
im totally in here !!
Top tier, lads!
The timing couldn't be better, I just spent an hour going back and forth in an audio editor piecing bits of generations together. My use case is more for sales presentations rather than audiobooks. I want to use a single voice but switch between default presets for the same voice to make her sound more excited or serious.
if I press the regenerate button on the project, will it reduce the package character quota that I have?
Please how does characters count works on eleven lab?
@@MondayAbiola Every space and character is counted. This sentence: "I drove to the store" is counted as 22 characters, including the quotes, and used against your credits. Without spaces and quotes, the character count is 16.
In a 3733-word document I created it had a total of 3717 spaces, and that's not even including the breaks between paragraphs, which, I believe, are also counted against your credits.
We definitely get charged for non-speech related characters. After testing and finding the right voice, you will waste lots of credits. Other companies are probably going to introduce a better model soon based on speech-only credits and take a lot of business away from them, i predict.
Can voices be assigned automatically for a screenplay?
That would be cool ... maybe easy with a Fountain formatted/text script. Fingers-crossed🤞🏼
@@DeusExMachina50 The screenplay is for an animation with AI voice overs.
How do I include Special Effects (from the Special Effecs Tab) in my Project Section?
Can you use the Speech-to-Speech module within Projects?
Brilliant!
Great! Well done
You create all this but dont have feature to slow down speech or add emotional tones to speech..
Hello, what's the best was to type out phone numbers and website address so they sound natural Please provide examples. Thank you.
How do I pause my recordings between chapters?
The character limit in text is a joke. I'm waiting for Microsoft to create competition because it's just a gimmick aimed at gaining additional funds, pay pay pay...
It's not that great. Blows pronunciation, and charges you for corrections. No clue as to putting together the pieces of a project to make a single audio book. Notice that this video promises you a lot but in spite of highlighting piees that in no way connect to fulfilling actual tasks, it's not showing you how to do anything. I plan to finish in ElevenLabs, correct in Audacity, and switch to Bowker
Goodness!!!
I'm becoming really frustrated with not being able to regenerate just ONE SECTION.
This is making my audio book take so much longer because there are no clear directives (or tutorials online) as to how to regenerate ONE sentence in a chapter. When I press regenerate the whole damn chapter regenerates and messes up a different section.
Será que esto también está en español?
can I use multiple voices with API ?
what's the background audio called
Eu usei 5 mil carateres e gerei a voz do Adam e não apareceu o botão de download e saiu da página.
Eu fiquei chateado e escrevi tudo de novo e a mesma coisa aconteceu e perdi ao todo 10 mil caracteres.
E fiquei sem postar minha matéria.
Eu quero que me devolvam os 10 mil carateres que não baixei.
A opção de download deveria aparecer assim que gerasse a voz e não obrigar as pessoas a ouvirem tudo. Eu faço tudo pelo celular
Wow. Used it for first time today. My credits got sucked up quick. Gotta be a better way to try before subscribing.
Hello, do you have any business personnel or agents in China?
awesome !!!
Losing it here, trying to download the entire text. Only downloads 19 seconds. Keeps highlighting small paragraphs. What gives?
This website gets useless after a while. I use this thing for stop motions and it says my character limit has ended and it says I need to pay to get more. Please fix this
Get ur money up its only 5$ lil bro
in the second month, they blocked all the voices and did not return the funds for the reason that they were allegedly not mine, only I installed them myself, twisted them so that it would be a female male or an old man’s voice, and as a result they took the money and derailed 1.5 months of my work.
Amazing
great!
Wowowowowowowowowoowowowowwow
This is a useless website, I created an account several times and each of them blocked me saying that you are using a VPN while I was not using any VPN.
It's not perfect. It still makes mistakes. If it mispronounces something in a paragraph or the flow is mismatched, it will fix it most of the time, not all the time and it will redo the whole paragraph, not just the one line, so it will cost you more. It's very easy to overspend correcting mistakes with this program even though for the most part it's great. Just be careful of the trap of constantly try to redo its errors. Turns into a money pit after that.
This is top utility to make audiolivr but I go to the Site and check the Books why very instable? Huge noise Look winny 1minuto little woman 28minuto
nice
I have no idea why it won't let me use the Scottish for my story when im paying so much 🤬🤬🤬🤬
Bring back Adam😭
The narrator is also ai
I think it is not
Given the context it wouldn't make sense to not make every voice in this video machine-based.
How can I buy by Apple Pay (iTunes )
Nah they making explain and making brainrot content