Skip to main content
Last Updated: March 18, 2025 By using our integrated custom LLM prompts, you can generate an action items list from your transcribed meetings. To use this, you just need to add the custom_prompt input parameter to your transcription request.

​
Custom input parameters

In this example, we’ll use a Python script to transcribe an audio file and tell it to use the custom_prompt input parameter to generate the action items. We’ll use the following input parameters: 
payload = {"input": {
        "custom_prompt": "The following is a meeting transcription. Summarize internally, and then generate a list of action items from the meeting. Only use real actions that make sense to do, ignore anything unimportant. Rewrite each task to be more clear and concise. Format it in a markdown compatible list to make it easy to read.",
        "url": audio_file_url,
        "diarization": True,
        "language_code": "en",
        "return_as_file": False
    }}

​
Python script

We’re going to create a file and name it action-items.py. We’re then going to use the above parameters in the following Python script: 
import requests
import time

audio_file_url = "url/to/audio/file.mp3" # replace with your audio file URL

salad_api_key = "YOUR_SALAD_API_KEY" # replace with your Salad API key
organization_name = "YOUR_ORGANIZATION_NAME" # replace with your organization name

payload = {"input": {
        "custom_prompt": "The following is a meeting transcription. Summarize internally, and then generate a list of action items from the meeting. Only use real actions that make sense to do, ignore anything unimportant. Rewrite each task to be more clear and concise. Format it in a markdown compatible list to make it easy to read.",
        "url": audio_file_url,
        "diarization": True,
        "language_code": "en",
        "return_as_file": False
    }}
headers = {
    "Salad-Api-Key": salad_api_key,
    "Content-Type": "application/json"
}


url = f"https://api.salad.com/api/public/organizations/{organization_name}/inference-endpoints/transcribe/jobs"

response = requests.post(url, json=payload, headers=headers)

response = response.json()
job_id=response["id"]
print (f'Job ID: {job_id}')

while True:
  time.sleep(5)
  try:
      result = requests.get(f"{url}/{job_id}", headers=headers)
      result = result.json()
      if result["status"] == "created" or result["status"] == "pending" or result["status"] == "started" or result["status"] == "running":
          print(f'Current job status is {result["status"]}')
      elif result["status"] == "failed":
          print(f'Job failed')
          break
      elif result["output"]:
          print(result["output"]["llm_result"])
          break
      else:
          print(f'Current job status is {result["status"]}')
  except Exception as e:
        print(f'Error retrieving transcription result: {e}')
        break
  • Make sure to replace url/to/audio/file.mp3 with the URL of your audio file.
  • Replace YOUR_SALAD_API_KEY with your Salad API key.
  • Replace YOUR_ORGANIZATION_NAME with your organization name.
  • Run the script using with python action-items.py.
In this script, we’re telling the LLM to read through the transcription, and generate a list of important action items. We’re also asking it to format it to be easily readable in markdown format. It will be returned in the llm_result field of the response. We’re then printing the result of this field to the console. Your console will look something like this once it finishes:

​
Output

Job ID: abcdef6c-1234-41e8-b81b-ecc1109033ed
Current job status is running
Current job status is running
Current job status is running
Current job status is running
Current job status is running
Current job status is running
Current job status is running
Current job status is running
Current job status is running
The meeting discusses migrating to Salad Transcription API from our existing provider.

**Action Items:**

* Schedule a follow-up meeting to discuss transcription migration with the team
* Assign tasks to team members for the new project
* Test out the Salad Transcription API for the next meeting
* Set up billing for Salad
* Onboard Aardvark to the project
* Configure the new server