Avatar and TTS (Text-to-Speech) API (beta)
Text-to-Speech and avatar resources are now available in private beta.
Overview
Avatar and Text-to-Speech (TTS) is a technology for creating digital clones of real humans which can be used to create lifelike speaking videos or audio from a transcript. These resources reduce creation time and cost for professional content production.
These APIs offer automated video and audio creation at scale:
- Avatar API enables you to create an avatar speaking on video from a provided transcript. You may provide audio or text input files.
- Text-to-Speech (TTS) API enables you to generate lifelike spoken audio from a provided transcript.
Start exploring this API to see what it's all about.
