Live Sessions

Everything in Aura Live revolves around a Live Session. A session is a temporary bridge between your audio source and our transcription engine.

Prerequisites

Before starting a session, you should identify:

1. Language: What language is being spoken? (Use the iso_639_1 code).
2. Model: Which ASR model should process the audio? (e.g., tiny, medium, large-v3).

Starting a Session

To start a session, send a POST request to the /api/v1/sessions/ endpoint.

Request Body

Specify the language and the base model you want to use.

{
  "language_id": 1,
  "model_id": 2
}

Response

The API will return a session object containing a session_id.

{
  "id": "abc-123-def",
  "status": "pending",
  "created_at": "..."
}

Session Life Cycle

1. Pending: The session is created but no audio is being received.
2. Active: Audio is being streamed and transcribed.
3. Finished: The connection has been closed by either the client or the server.
4. Error: Something went wrong with the transcription engine.

Fetching Available Options

To populate your session configuration, use these endpoints:

• List Languages: GET /api/v1/languages/
• List Models: GET /api/v1/models/

[!TIP] Use the models’ vram field to understand the resource requirements. Smaller models like tiny are faster but less accurate, whereas large-v3 provides the highest accuracy but requires more compute.