> ## Documentation Index
> Fetch the complete documentation index at: https://docs.salad.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How to Automatically Follow Sales Playbooks with Salad Transcription API

*Last Updated: March 28, 2025*

By using our integrated custom LLM prompts, you can automatically follow a Sales Playbook from your transcribed meetings
and sales calls to help meet your KPIs. 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 answer questions in our mock playbook. We'll use the following input parameters:

```python theme={null}
payload = {"input": {
        "custom_prompt": "The following is a sales call transcription. Follow the playbook and answer the questions. If there are no answers, say 'No answer'. Question 1: Did the sales person get the customers name? Question 2: Did the sales person correctly understand the customers requirements? Question 3: Did the sales person ask for the customer's pain point with their existing providor? Question 4: How well and precisely did the sales person answer questions posed by the customer? Question 5: Did the sales person ask the customer how the call went?",
        "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 `playbook.py`. We're then going to use the above parameters in the following
Python script:

```python theme={null}
import requests
import time

audio_file_url = "https://your-storage.com/path/to/audio.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 sales call transcription. Follow the playbook and answer the questions. If there are no answers, say 'No answer'. Question 1: Did the sales person get the customers name? Question 2: Did the sales person correctly understand the customers requirements? Question 3: Did the sales person ask for the customer's pain point with their existing provider? Question 4: How well and precisely did the sales person answer questions posed by the customer? Question 5: Did the sales person ask the customer how the call went?",
        "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 `https://your-storage.com/path/to/audio.mp3` with the URL of your audio file.
* Replace `YOUR_SALAD_API_KEY` with
  [your Salad API key](/container-engine/tutorials/quickstart-api#step-1-obtain-your-api-key).
* Replace `YOUR_ORGANIZATION_NAME` with your organization name.
* Modify the questions in the `custom_prompt` parameter to match your playbook.
* Run the script using `python playbook.py`.

In this script, we're telling the LLM to answer our questions and fill in the sales playbook. 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

```text theme={null}
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
Transcription Result: Question 1: Did the sales person get the customer's name?
Yes.

Question 2: Did the sales person correctly understand the customer's requirements?
Yes.

Question 3: Did the sales person ask for the customer's pain point with their existing provider?
No.

Question 4: How well and precisely did the sales person answer questions posed by the customer?
Good, provided relevant information about NVIDIA 50 series controversy.

Question 5: Did the sales person ask the customer how the call went?
No.
```