This feature is in Alpha state.We’re looking for feedback to improve this feature, share yours on Discord.
The Audio to LLM feature applies your own prompts to the audio transcription. For now, it is only available for pre-recorded audio.

​
Usage

Enable Audio to LLM by setting the appropriate flag and providing your prompts: 
{
  "audio_to_llm": true,
  "audio_to_llm_config": {
    "prompts": [
      "Extract the key points from the transcription as bullet points",
      "Generate a title from this 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 the results for each prompt under the results key.