How do I generate multiple clip variations?

Introduction: Generating clip variations

In Resemble AI, you have the flexibility to generate multiple variations of a clip to ensure you get the desired result. This feature is particularly useful if you're not satisfied with the initial clip generated by the model. In this knowledge base article, we'll guide you through the process of generating clip variations to find the option that best suits your needs.

Generating Clip Variations:

1. Initial Clip Generation:
Start by generating the initial clip using the text to speech text box. 

2. Reviewing the Initial Clip:
Once the initial clip is generated, review it carefully to determine if it meets your requirements. If you're satisfied with the clip, you can proceed with using it for your project.

3. Generating Additional Options:
If you're not satisfied with the initial clip, you have the option to generate three more variations. To do this: Above the text box there is a 👍 button.
Screenshot 2024-02-27 at 10.48.57 AM-14. Selecting the Preferred Option:
After generating the additional variations, review all four options to determine which one best fits your needs. You can listen to each variation and compare them to choose the preferred option.

5. Finalizing Your Selection:
Once you've selected the preferred clip variation, you can proceed with using it for your project. If you still have concerns or if none of the variations meet your requirements, you may consider refining your input text or adjusting other parameters before generating new variations.

Generating clip variations in Resemble AI provides you with the flexibility to explore multiple options and select the one that best suits your needs. Whether you're looking for a specific tone, style, or emphasis, this feature allows you to fine-tune your clips to achieve the desired result. By following the steps outlined in this article, you can efficiently navigate the clip generation process and find the perfect option for your project.


Will I be charged for generating multiple? 
Yes, we charge for synthesizing audio, when users are generating multiple, we are synthesizing audio for those variations.