Speech-to-text audio transcription
Text-to-speech
Text-to-speech (TTS) is a feature in the Vivox SDK that is intended to support developers who are pursuing Communications and Video Accessibility Act (CVAA) compliance.
Note: TTS is only available in US English, and is only supported for one logged in user.
TTS provides a voice channel participant with the ability to convert text messages into synthesized speech that is then transmitted into the voice channel. This allows a user to participate in voice chat even when they might not be able to speak or speak clearly. TTS also provides a user with the ability to convert text chat or game-screen text into synthesized speech for local playback.
You can play a synthesized phrase locally through the user’s output audio device, transmit it and play it back for remote participants, or simultaneously play it locally and transmit it to remote participants.
Note: Unlike with the Vivox Core SDK, the engine wrappers do not require manual initialization of text-to-speech to start using it. Also, clean up is handled automatically.
| Related pages | Description |
|---|---|
| Text-to-speech voice options | Choose a synthesized voice for your text-to-speech messages. |
| Text-to-speech destinations | Control where text-to-speech messages are played. |
| Inject a text-to-speech message | Inject a text-to-speech messages into a channel or local audio. |
| Queue a text-to-speech message | How to manage a queue of text-to-speech messages. |
| Cancel a text-to-speech message | Cancel an ongoing or queued text-to-speech message. |