What are best practices for creating projects?

Creating projects in Resemble AI

Best Practices for Building TTS and STS Projects

Introduction: Efficiently creating projects in Resemble AI's user interface is crucial for achieving the best quality output. In this knowledge base article, we will provide you with some essential best practices to consider when building your TTS (Text-to-Speech) and STS (Speech-to-Speech) projects.

Building Projects in the Resemble UI:

Project Size Consideration: When working with TTS and STS projects, it's essential to consider the project size for optimal results. The following guidelines will help you achieve the best quality output:

  1. Sentences per Text Box:

    • Limit the number of sentences per text box to a maximum of 3. This ensures that the AI model can focus on generating accurate and expressive speech for a smaller set of sentences.
  2. Number of Characters per Project:

    • Aim for a project size between 2,500 to 3,000 characters. Staying within this range allows you to download the output as individual .wav files, which can be useful for organization and post-processing.
  3. Number of Sentences:

    • Keep the number of sentences within a project to a maximum of 150. This helps maintain efficient processing and quality throughout your project.

Project Hacks for Enunciation: Sometimes, you may encounter pronunciation challenges with the AI models. Here are some useful tips to work around these issues and enhance the pronunciation of your text:

  1. Use Punctuation:

    • Add punctuation marks before or after a word to help guide the model in pronunciation. For example, placing a comma or period can influence the pronunciation of adjacent words.
  2. Double Letters:

    • Consider doubling letters, whether vowels or consonants, in the words to achieve specific sounds. For example, changing "Say" to "Saay" can result in a more accurate representation of the long 'A' sound.
  3. Capitalizing Letters:

    • Capitalizing letters can create emphasis on the letter in the word. For example, "request" can be spelled as "requeST" for an emphasis on the 'ST' sound at the end.
  4. Split Paragraphs:

    • If the model struggles to pronounce all the words in a paragraph, consider breaking the paragraph into separate sentences. This can significantly enhance the pronunciation of individual words and phrases.

Getting Further Assistance: If you encounter persistent issues or have specific challenges that require additional support, please don't hesitate to reach out to our dedicated support team at Support@Resemble.ai. Our team members are ready to assist you and provide guidance to ensure your project's success.

Conclusion: By following these best practices, you can optimize your Resemble AI projects for exceptional output quality and achieve the desired results for your TTS and STS endeavors.