Hello, It's Vivek with holding scale plan of 330$Today, my custom cloned voice made by (IVC) becam

[tidal wave]

AI-generated Answer for vivuraj

I'm sorry to hear that you're having trouble with your cloned voice. There could be several reasons why your voice clone doesn't sound as expected.

One possibility is that the quality of the samples you're using for cloning has changed. The AI will attempt to mimic everything it hears in the audio, including the speed of the person talking, the inflections, the accent and tonality, breathing pattern and strength, as well as noise and mouth clicks. If there's too much variance in these factors, it might confuse the AI, leading to more varied output between generations.

Another important thing to keep in mind is that the AI will try to replicate the performance of the voice you provide. If you talk in a slow, monotone voice without much emotion, that is what the AI will mimic. On the other hand, if you talk quickly with much emotion, that is what the AI will try to replicate.

If you have a rather unique voice with a less common accent, instant voice cloning might not provide a perfect replication of your voice. In such cases, professional voice cloning might be a better option.

Unfortunately, there is no way to influence the accent or tone of the clone after the clone has already been created; the only way to influence it is to change the actual samples you use for cloning. Just small changes to the samples can make a big difference.

If you're still having trouble, it might be best to reach out to the support team for further assistance.

[paper shoal]

We're experiencing the exact same thing! Thanks for raising, Vivek. Hoping @tidal wave may be able to roll something back. Our voices on Multilingual V2 are massively degraded as of today.

[tidal wave]

AI-generated Answer for jonny_richards

I'm sorry to hear that you're experiencing issues with your cloned voice. The inconsistency you're experiencing can sometimes occur with AI, as it can be unpredictable at times. However, there are a few things you can do to minimize this unpredictability.

Firstly, it's important to ensure that you're using high-quality samples that are very consistent. This will help tremendously in maintaining consistency. For Instant Voice Cloning, you should use around 1 to 2 minutes of audio. This audio should be very consistent across all aspects such as tonality, performance, accent, quality, and so on, if you want the output to be consistent. Using more audio than that can make the AI too variable, which can cause inconsistency between generations.

If you're already cloning the voice, try cloning the voice again with different samples if you encounter a lot of variability. It might require a bit of experimenting if you don’t get it right the first time.

Also, both stability and similarity settings can change how the voice acts as well as how prominent the artifacts are. Adjusting these settings might help in improving the voice quality.

Lastly, if the issue persists, it might be beneficial to use the Projects feature, which is a bit more advanced than Speech Synthesis when it comes to long-form content. This feature was specifically made for that and it seems to minimize the issue of inconsistency.

I hope these suggestions help in resolving the issue you're facing with your cloned voice.

[vagrant cradle]

I have the same issue actually. I’ve been using Multilingual V2 for the past few months for my cloned voice and it was perfect. When I tried it just today, the voice itself was off, and the quality itself was bad. I hope this can be fixed

[tidal wave]

AI-generated Answer for silentsomnolence_06495

I'm sorry to hear that you're experiencing issues with the Multilingual V2 model. The AI can sometimes be unpredictable, and the output quality can vary based on the input. However, there are a few things you can do to improve the situation.

One of the issues you might be facing is inconsistency. This can happen more to certain voices than others and when the samples for those voices are suboptimal, which most often means not following the guidelines. If you encounter a lot of variability, you could try using a cloned voice or, if you are already cloning the voice, try cloning the voice again with different samples.

For consistency, you should use around 1 to 2 minutes of audio when Instant Voice Cloning. This audio should be very consistent across all aspects such as tonality, performance, accent, quality, and so on, if you want the output to be consistent. Using more audio than that can make the AI too variable, which can cause inconsistency between generations.

For Professional Voice Cloning, we recommend at the very least 30 minutes of audio and suggest between 2 to 3 hours of audio for the best results. Keep in mind, the audio needs to be consistent throughout for the best result.

Another issue could be mispronunciation. The multilingual v2 model does have a fairly rare issue where the AI mispronounces certain words, even in English. The best way to deal with this is to use the Projects feature, which seems to minimize the issue as it is more prevalent across longer sections of text when using Speech Synthesis.

Lastly, the AI can sometimes switch languages or accents throughout a single generation, especially if that generation is longer in length. Using a proper clone paired with Projects which has been cloned speaking the language you want the AI to speak should again help mitigate most of this.

I hope these suggestions help you improve the quality of your voice generations.

[trail swift]

1. I've been facing the same issues with Multilingual V2 and Turbo V2.5 where My fine tuned voices were fine 2 days ago then towards the next day they are now sound completely different and British sometimes. This is the second time aftere we fine tuned from some other update on Sunday. My team and I have decided to postpone our launch again due to this, please would love some support