A repo to collect some artifacts to process a raw text file and get audio output using one of Azure's pre-built voices. To see the sample voices, look here. To use one of the Azure OpenAI voices, you may have to have an OAI resource in a specific region. This is helpful to create audio outputs for material when an acoustic medium is preferred.
Attribution to the code files present here, with the main documentation here. This leverages REST calls vs. the Speech SDK. Batch synthesis code examples here.
To run through steps, reference the Makefile.