With my PVC, the Multilingual v2 and the Turbo v2 models produce the same high similarity to my act | ElevenLabs | Page 1

fiery oracleBOT Jul 21, 2024, 4:30 PM

#

AI-generated Answer for adamtwar

Based on the information provided, the Turbo v2 and Multilingual v2 models are designed to provide high-quality voice cloning. However, the Turbo v2 model is specifically optimized for low-latency applications and is an English-only model. It might have slightly lower accuracy than the Multilingual v2 model due to its optimized nature.

The Multilingual v2 model, on the other hand, has great language diversity and fantastic accuracy in cloning voices and accents. It's worth noting that this model will strive to clone everything present in the original samples with even greater precision than other models. This includes the performance, accent, and tone of voice you want the AI to clone.

As for the Turbo 2.5 model, it's not mentioned in the provided information. Therefore, it's hard to provide a specific reason why the English generation from this model sounds different. It could be due to the model's specific characteristics, training data, or other factors.

Remember, the quality of the voice clone can also be influenced by the quality and consistency of the samples you provide. Using proper, high-quality samples with the performance, accent, and tone of voice you want the AI to clone is recommended.

mint imp Jul 21, 2024, 4:37 PM

#

Why is my cloned voice delaying between the sentences and it's not a normal delay it's too much

fiery oracleBOT Jul 21, 2024, 4:37 PM

#

AI-generated Answer for nonstopjokes.

Your professional voice clone might experience a few different states, such as being "delayed". If your professional voice clone is delayed, it will automatically retry periodically and attempt to clone again. You do not have to take any action, as all of this will be automatic. However, keep in mind that it may retry multiple times before succeeding, or in the worst case, you might encounter a different error.

If your voice has already been tried multiple times and AI still cannot clone the data that you provided, there might be an issue with the dataset that the AI cannot resolve. What you can try doing is deleting the voice and uploading the data again, starting from the beginning. This has been shown to help some users. The ideal approach would probably be to review your datasets and see if you can use different data to hopefully clone your voice since uploading the same data might work, but it might also be the reason why the AI is having issues to begin with.

mint imp Jul 21, 2024, 4:39 PM

#

In the text to speech area when I click generate it's delaying between the sentences and it's not normal delay it's too much and even it's delaying between the words

#With my PVC, the Multilingual v2 and the Turbo v2 models produce the same high similarity to my act