Avoid Generating Boring Synthesized Speech

January, 21 2022

Chant Developer Workbench Enables Applications Better Control Over TTS

Speaking qualities such as the speed, pitch, emphasis, and word pronunciation may be tailored in reproducing speech from text.

Speech APIs support two primary ways to control synthesis: properties and markup.

With properties, applications set options for synthesis that persist for all subsequent requests.

With markup, text to be synthesized is annotated with options to be applied only when processing that request.

Review what properties and markup can do at Chant Knowledge Base article H072123.