> ## 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.

# Transcription API Python SDK Quick Start

*Last Updated: July 25, 2025*

This quick start tutorial will teach you the basics of using the **Salad Transcription API Python SDK**. It demonstrates
how to install the SDK, authenticate with your API key, submit transcription jobs, and access results.

***

## Prerequisites

Before you begin, ensure that:

* You have a **SaladCloud account** and a valid **API key**. Generate one via the Salad Portal.
* You have **Python 3.9+** with `pip` properly configured on your system.

***

## Step 1: Install the SDK

Install the SaladCloud Transcription SDK using pip:

```bash theme={null}
pip install salad-cloud-transcription-sdk
```

## Step 2: Submit a file for transcription and retrieve the result

The following example demonstrates how to transcribe a local audio or video file.

Replace:

* `<YOUR_API_KEY>` with your SaladCloud API key
* `<ORG_NAME>` with your organization name
* `<FILE_PATH>` with the path to your local file (or use a downloadable URL)

```python theme={null}
from salad_cloud_transcription_sdk import SaladCloudTranscriptionSdk
from salad_cloud_transcription_sdk.models.transcription_job_input import TranscriptionJobInput
from salad_cloud_transcription_sdk.models.transcription_request import TranscriptionRequest

# Initialize the SDK with your API key
sdk = SaladCloudTranscriptionSdk(api_key="<YOUR_API_KEY>")

# Configure the transcription job parameters
request = TranscriptionRequest(
    options=TranscriptionJobInput(
        language_code="en",
        srt=True,
        return_as_file=False,
    ),
    metadata={"project": "quick_start_example"},

# Submit the job and wait for it to finish
job = sdk.transcribe(
    source="<FILE_PATH>",
    organization_name="<ORG_NAME>",
    request=request,
    auto_poll=True  # Automatically waits until the job completes
)

# Print the transcript text
print("Transcript:\n", job.output['text'])

# Access full JSON output (timestamps, SRT, metadata)
print("\nFull output object:\n", job.output)
```

## Next Steps

You should now have a working transcription pipeline. To learn more:

* Explore [Code Examples](/transcription/how-to-guides/sdk/python-sdk-examples) for polling jobs options, webhook
  handling, Lite vs. Full engine usage and parameters setup.
* Review the [Full Documentation](/transcription/how-to-guides) for advanced features like summaries, translations,
  custom vocabulary, and sentiment analysis.