# Synthesizers A *synthesizer* is able to learn information about your real dataset, and use it to create synthetic data that matches the format and mathematical properties. Each synthesizer runs through two steps: 1. **Model**: In this stage, the synthesizer uses various methods (typically machine learning) to learn a model from the real data 2. **Sample**: Once the model has been learned, the synthesizer can use it to create synthetic data All synthesizers in SDGym follow these steps. The benchmarking scripts will return several, descriptive statistics about each phase. ## Which synthesizers can I use? The SDGym library includes synthesizers that are ready to use. You can also create a custom synthesizer based on your own methods.


SDV Synthesizers	Use a synthesizer from the open source SDV library.	/pages/FDjWQgL42xtKDcbTnBF2
Basic Synthesizers	Use a basic data generator as a baseline to compare other synthesizers.	/pages/bCznuI5UPPfItVbWbdKY
3rd Party Synthesizer	Use a synthesizer from an external library for benchmarking.	/pages/lGzRlIBStn4bVLZ5Q6yM
Your Custom Synthesizer	Define your own, custom technique for creating synthetic data.	/pages/l7lFI8qW55UvfeF53fZY

--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.sdv.dev/sdgym/customization/synthesizers.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.