The Google Cloud Text-to-Speech API converts text input into audio data of human-like speech in more than 100 voices across more than 20 languages. With the API, developers can create interactions with users that are aimed to feel more lifelike. This API uses RESTful calls although there is a gRPC version of the API also available.
Text to Speech (TTS) technology is useful for providing audible content from text for accessibility and language translation. The ProgrammableWeb TTS category contains developer resources for adding the technology to applications, including SDKs, code samples and APIs like the 9 in this article.
Google has announced updates to the Cloud Text-to-Speech API that will provide developers with 12 new languages/variants as well as 76 new voices. The API now includes 95 WaveNet voices, which the company claims are far more natural-sounding.
Thirteen APIs have been added to the ProgrammableWeb directory in categories including Blockchain, Events, Transcription, and Sports. One highlight is the Europeana Record API for retrieving data about Europe's art and historical artefacts. Here's a rundown of the latest additions.
Google has announced updates to its Cloud Speech to Text and Text to Speech APIs that include additional languages, voices, and more affordable pricing models. The goal of these updates is to help developers build better intelligent voice applications and make the products more widely available.