Load Opus Clip data to DuckDB

OpusClip is an AI-powered platform for transforming long-form videos into short, viral clips and managing automated video workflows. Everything needed to build a working Opus Clip → DuckDB pipeline is on this page: the API's base URL, authentication, endpoints, pagination and incremental field — plus a prompt that hands the whole job to your coding agent.

---

Build your Opus Clip to DuckDB pipeline

Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.

PromptCopy prompt
Run uvx dlthub-init@latest to build a pipeline from Opus Clip to DuckDB and run it on dltHub

That scaffolds a dltHub workspace and installs the dltHub AI harness — the project rules, the secrets-management skill, and the dlt MCP server your agent needs to work safely. From there it reads the Opus Clip API, proposes the endpoints to load, then writes, runs and validates the pipeline while you review rather than type. Credentials are inspected through MCP tools, so your agent never reads secrets.toml itself. How the LLM-native workflow works →

Prefer to write it yourself? Every fact the agent uses is below.

---

Opus Clip API at a glance

These values come from the Opus Clip API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Opus Clip API?

Authentication is performed by passing an API key in the Authorization header. While most documentation examples use the format 'Authorization: Bearer <API_KEY>', some endpoints specifically show 'Authorization: <API_KEY>' without the Bearer prefix.

1. Get your credentials

To obtain your Opus Clip API credentials, log in to your account and navigate to the Opus Clip dashboard at https://clip.opus.pro/dashboard. You can find your organization’s API access key in the lower left corner of the dashboard. Ensure your account is on a Pro (Beta), Max, or Business plan to access the API.

2. Add them to .dlt/secrets.toml

Copy
[sources.opus_clip_source]
api_key = "your_actual_api_key_here"

dlt reads this file automatically at runtime. With the harness, the setup-secrets skill prompts you for the values and never handles the raw credential in chat. For production, see setting up credentials with dlt.

---

What Opus Clip data can I load into DuckDB?

These are the Opus Clip endpoints dlt can load into DuckDB:

---

How do I load only new Opus Clip records?

Opus Clip exposes pageNum on api/exportable-clips, so dlt can request only the records that changed since the last run. Set it as the cursor_path and dlt tracks the high-water mark for you between runs.

Copy
{"name": "exportable_clips", "endpoint": {
    "path": "api/exportable-clips",
    "incremental": {"cursor_path": "pageNum", "initial_value": "2024-01-01T00:00:00Z"},
}}

On the first run dlt loads everything from initial_value; on every run after that it requests only what changed and appends with write_disposition="merge" if you set a primary key. See incremental loading.

---

What does the generated Opus Clip pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /api/clip-projects and /api/exportable-clips from the Opus Clip API into DuckDB:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def opus_clip_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.opus.pro",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "exportable_clips", "endpoint": {"path": "api/exportable-clips"}},
            {"name": "clip_projects", "endpoint": {"path": "api/clip-projects"}}
        ],
    }
    yield from rest_api_resources(config)


def load_opus_clip_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="opus_clip_pipeline",
        destination="duckdb",
        dataset_name="opus_clip_data",
    )
    load_info = pipeline.run(opus_clip_source())
    print(load_info)


if __name__ == "__main__":
    load_opus_clip_to_duckdb()

Run it with python opus_clip_pipeline.py. The agent iterates on this until it loads cleanly — you review and approve, rather than write it from scratch.

---

How do I query Opus Clip data in DuckDB?

dlt creates one table per resource. Query the loaded data with Python or SQL — or ask your agent to, through the MCP server's execute_sql_query tool.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("opus_clip_pipeline").dataset()
df = data.exportable_clips.df()
print(df.head())

SQL:

Copy
SELECT * FROM opus_clip_data.exportable_clips LIMIT 10;

See querying your data with dataset and exploring it in marimo notebooks.

---

How do I deploy the Opus Clip to DuckDB pipeline in production?

The pipeline runs locally, which is ideal for prototyping and one-off analysis. When you need it on a schedule, monitored on every load, and shared with your team, deploy the same dlt code on the dltHub platform — no infrastructure to maintain. The prompt above already ends with "run it on dltHub", so your agent can take it there directly.

• Deploy & schedule — run the pipeline as a managed job with automatic retries.
• Monitor — observable job queues, alerting, and load metrics for every run.
• Transform — promote raw Opus Clip loads into governed, documented models.
• Visualize & share — explore data in notebooks and publish live dashboards instead of static screenshots.

Book a demo →

---

What other destinations can I load Opus Clip data to?

dlt loads into any of these — only the destination argument changes:

Set dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. On the dltHub platform the same pipeline runs against a managed Iceberg lakehouse. See the full destinations list.

---

Next steps

• Ready for production? Book a demo of the dltHub platform →
• dlt LLM-native workflow docs
• REST API source reference
• Join the dlt community on Slack