Important: This is documentation for the legacy version of the Vivox Unity SDK. This documentation will be removed after July 2025. Refer to the v16 documentation for the new version of the SDK.
Speech-to-text
Speech-to-text audio transcription is an optional paid Vivox service that allows per-user enablement of speech transcription in one or more connected non-positional or positional voice channels. For pricing information and to discuss enabling this service for your organization, contact your sales representative.
This service supports developers pursuing Communications and Video Accessibility Act (CVAA) compliance.
Customers with speech-to-text transcription enabled can provide transcribed audio to any user who has opted into receiving it on a per-channel basis. Transcribed audio is returned in text message format with an indication that the message was transcribed from voice. These messages can also indicate if the transcribed text is from the user who requested transcription.
| Topic | Description |
|---|---|
| Audio transcription conditions | Details on conditions where transcription can occur. |
| Audio transcription delivery | Where transcribed messages are delivered within the Vivox SDK. |
| Enable speech-to-text transcription | How to enable speech-to-text transcription in a channel. |
| Disable speech-to-text transcription | How to disable speech-to-text transcription in a channel. |
| Audio transcription language support | Details on speech-to-text language support. |
| Audio transcription error codes | Specific Vivox error codes related to speech-to-text. |