Overview

You can find more information about using the speech synthesis function here, including some tips that can bring better results.

After you have added or created some new characters, you can start using them to generate some speech! To perform Text-to-Speech (TTS), please go to the Vocu Studio page, add or edit the text you need there, assign characters (speakers) to paragraphs, then click the Start Generation button in the Generation Configuration tab and you're done!

It's simple, isn't it? However, there are a few things you may need to pay attention to:

• Due to the characteristics of AI models, the results generated each time are slightly different. You can try several times to get ideal or more creative effects.

• Generation parameters have a great impact on the final generation effect. Currently, based on various tests and optimizations, we have set different preset templates, each corresponding to different optimization directions. You can choose different generation parameters by adjusting presets to find the most suitable effect for you.

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