> ## 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.

> ## Agent Instructions
> For autonomous tasks, use live SaladCloud API responses for current state, availability, quotas, models, and other dynamic values. Use current OpenAPI specifications where provided for paths, schemas, required fields, and enums. Never invent endpoints, fields, prices, availability, quotas, models, or state. Prefer API workflows over Portal steps. Read before changing and never expose credentials, signed media URLs, prompts, or sensitive outputs. Retry only safe or idempotent operations with bounded backoff, honoring Retry-After. Verify every write with a read. Stop rather than repeat an uncertain non-idempotent or billable request. AI Gateway uses an organization-specific Bearer key and live /v1/models discovery. Do not delete, cancel, stop, or reduce capacity without explicit user intent. Bind shared operation IDs to the selected product path. Treat Container Engine instances as interruptible and local state as ephemeral. Install the SaladCloud skills (npx skills add https://docs.salad.com), start from the salad skill and /agents/overview; docs MCP: https://docs.salad.com/mcp.

# Transcription API Python SDK Quick Start

*Last Updated: August 24, 2026*

> Before using SDK convenience polling or webhook helpers, validate the underlying request against the selected OpenAPI
> schema and follow [Transcription preflight](https://docs.salad.com/agents/transcription/choose-api-and-preflight.md). A helper's create
> response still requires capture of the server job ID and a terminal verification read.

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


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.