Last Updated: March 05, 2025 By using our integrated custom LLM prompts, you can extract the important quotes from your transcriptions. 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 extract quotes from the transcription. We’ll use the following input parameters: 
payload = {"input": {
        "custom_prompt": "extract the most engaging quotes from the text. Put quotation marks around the quotes. For example, \"I love Salad\". Do not do any formatting to the list, or include any other text.",
        "url": audio_file_url,
        "language_code": "en",
        "return_as_file": False
    }}

​
Python script

We’ll use it in the following Python script: 
import requests
import time

audio_file_url = "url/to/audio/file.mp3"

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": "extract the most engaging quotes from the text. Put quotation marks around the quotes. For example, \"I love Salad\". Do not do any formatting to the list, or include any other text.",
        "url": audio_file_url,
        "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
In this script, we’re telling Salad to extract the most engaging quotes from the transcription. The quotes will be returned in the llm_result field of the response. We’re then printing the result of this field to the console. It’ll look something like this once it finishes:

​
Output

Job ID: abcfaf6c-7323-41e8-b81b-ecc7709066ed
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
"Deploy AI/ML production models at scale securely on the world's largest distributed cloud network. Save up to 90% on compute costs compared to high-end GPUs & hyperscalers."
"SaladCloud offered us the lowest GPU prices in the market with incredible scalability."
"Welcome to the compute-sharing economy! 90% of the world’s compute resources (over 400 million consumer GPUs) sit idle for 20-22 hrs daily."
At this time, timestamps are not supported for extracting quotes. The custom llm_prompt only views the “text” field response from the transcription completion, and so currently is unable to see the timestamps of the quotes.