Gartner defines speech-to-text (STT) platforms as business applications that process speech content, either live or in batch to produce: A transcript of the conversation Metadata about the call, the callers, attributes of call, emotional context Value-added services (e.g., biometric, legal) Workflow tools to support downstream work (e.g., intent detection, CRM updates) The capabilities of STT solutions vary. At a minimum, providers can offer a set of generic APIs with no tailored industry offering. More advanced solutions support complex deployments of edge technologies tailored to specific industries such as medical and legal. As natural language experiences are rapidly adopted by customers, users and employees, STT solutions must address a number of deployment configurations and be tailored for end-user domain knowledge to improve their accuracy.