Turning Text Into Speech

Today we’re excited to launch the POST /synthesize API, our speech synthesis solution! Speech synthesis, or text-to-speech, generates human-like speech from a text input.

By using the POST /synthesize API, you will now be able to respond to your customers using the same modality. It’s the perfect complement to any POST /speech integration!

You can now engage your audience with voice for a more natural experience. Speech synthesis empowers your customers to listen to messages if they choose to. This technology also gives a voice to non-player characters (NPCs) in games. Text-to-speech will be available in the upcoming v42 release of the Oculus Voice SDK.

The list of available voices and parameters is available using GET /voices. We currently support English (US). Note that like other endpoints, POST /synthesize is optimized for short inputs.

As always, please feel free to reach out if you have any questions, comments or suggestions.

Thank you for being part of this journey!

Wit.ai Team