Netlify Function: transcribe

This Netlify serverless function provides a backend for the omdTranscriptionService. It receives an image, sends it to the Gemini API for transcription, and returns the result.

Endpoint

/.netlify/functions/transcribe

Method

POST

Request Body

The request body should be a JSON object with the following properties:

• imageBase64 (string, required): The base64 encoded image data (without the data:image/png;base64, prefix).
• prompt (string, optional): A custom prompt to guide the transcription. If not provided, a default prompt for mathematical expressions is used.

Responses

Success Response (200 OK)

A successful response will be a JSON object with the following properties:

• text (string): The transcribed text.
• provider (string): The transcription provider used (always 'gemini').
• confidence (number): The confidence score of the transcription (currently hardcoded to 1.0).

Error Responses

• 400 Bad Request: This error is returned if the imageBase64 property is missing from the request body.
• 500 Internal Server Error: This error is returned if there is an issue with the transcription process on the server, such as an error from the Gemini API.

Environment Variables

This function requires the following environment variable to be set in your Netlify environment:

• GEMINI_API_KEY: Your API key for the Gemini service.

CORS

The function is configured to allow cross-origin requests from any origin.