Speech-to-Text Overview
Updated
Real-time transcription, translation, and caption recording using the Speech-to-Text REST API.
The Speech-to-Text REST API provides server-side access to real-time transcription, translation, and caption recording. Start and manage transcription agents that join your RTC channels and output captions from your backend.
API basics
All requests are sent to the host api.agora.io.
- Authentication: All APIs require Basic Auth for authentication.
- Request: Refer to the respective API examples.
- Response: The response content is in JSON format.
- Base URL:
https://api.agora.io/api/speech-to-text/v1/projects/<appid>where<appid>is the Agora app ID for your project.
REST APIs
- Start a Real-time STT agent: Creates and starts a transcription task that joins the specified RTC channel.
- Query the task status: Retrieves the status of a transcription task.
- Stop a Real-time STT agent: Stops a running transcription task.
- Update task configuration: Updates the configuration of a running transcription task.
- List Real-time STT agents: Retrieves the list of transcription tasks for the project.