Overview

Here you can find more information about using speech synthesis features, including some tips that can bring better results.

After you add or create some new characters, you can start using them to generate some speech! To perform Text-to-Speech (TTS), go to the Speech Synthesis page, add or edit some text freely, assign characters to them, and then click the Start Generation button in the Generation Configuration tab to complete it!

Simple, isn't it? However, there are a few points that may need your attention:

• Due to the characteristics of AI models, each generation will produce different results, so in order to get the effect you want, you may need to try multiple times for one sentence.

• Generation parameters have a significant impact on the final generation effect. If you need to adjust them, it is recommended to start with the default parameters of different generation styles and make small adjustments to their values to find the most suitable effect for you.

• Different versions of models may have some shortcomings and limitations. We recommend that you refer to the Model List to understand the introduction of each model.