Here’s a quick guide to integrate the Nexara Transcription API with n8n:

  1. Add HTTP Request Node: Search for and add the HTTP Request node to your n8n workflow.

  2. Import cURL Command: Click the “Import cURL” option within the HTTP Request node. Paste the following command, making sure to replace YOUR_NEXARA_API_KEY with your actual Nexara API key:

    curl --request POST \
--url https://api.nexara.ru/api/v1/audio/transcriptions \
--header 'Authorization: Bearer YOUR_NEXARA_API_KEY' \
--header 'Content-Type: multipart/form-data'

  3. Configure Body Parameters:

    • Scroll down to the Body section of the node’s parameters.
    • Ensure Body Content Type is set to Form-Data.
    • Under Body Parameters, click “Add Parameter”.
    • Set the Parameter Type to n8n Binary File. However, if you have the link to the file, just send the link to the file as a url parameter to the API.
    • Set the Name field to file.
    • Set the Input Data Field Name to data. (This assumes the binary file data from a previous node, like “Read Binary File”, is available under the data field. Adjust if your field name is different.)

  4. Done! (Add Optional Parameters): Your basic setup is complete! The node will now send the file for transcription.

    • To add other API parameters (like language, or response_format), add more parameters under Body Parameters, typically using String as the Parameter Type. Like this:
    • Make sure a node before this HTTP Request node reads your audio file and makes its binary data available (usually in the data field). Or just send the link to the audio file using the url parameter.
    • If you want to perform speaker diarization, you can add the task parameter to the API request and set it to diarize.

    For details on all available API parameters, please refer to the API Documentation.