This feature is on Alpha state.

We’re looking for feedbacks to improve this feature, share yours here.

The Audio to LLM feature applies your own prompts to the audio transcription.

With this code, your output will look like this:

{
  "success": true,
  "is_empty": false,
  "results": [
    {
      "success": true,
      "is_empty": false,
      "results": {
        "prompt": "Extract the key points from the transcription as bullet points",
        "response": "The main entities key points from the transcription are:\n- ..."
      },
      "exec_time": 1.7726809978485107,
      "error": null
    },
    {
      "success": true,
      "is_empty": false,
      "results": {
        "prompt": "Generate a title from this transcription",
        "response": "The Great Title"
      },
      "exec_time": 1.7832809978258485,
      "error": null
    }
  ],
  "exec_time": 6.127103805541992,
  "error": null
}

You’ll find your custom prompts results of your audio under the results key.

Was this page helpful?