Load Naver CLOVA Speech Recognition data to DuckDB

Naver CLOVA Speech Recognition is a REST API service that converts speech to audio files into text. Everything needed to build a working Naver CLOVA Speech Recognition → 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 Naver CLOVA Speech Recognition 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 Naver CLOVA Speech Recognition 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 Naver CLOVA Speech Recognition 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.

---

Naver CLOVA Speech Recognition API at a glance

These values come from the Naver CLOVA Speech Recognition API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Naver CLOVA Speech Recognition API?

Authentication is performed by passing a Client ID and Client Secret in the HTTP headers 'x-ncp-apigw-api-key-id' and 'x-ncp-apigw-api-key', respectively. These credentials must be obtained from the NAVER Cloud Platform console after registering an application.

1. Get your credentials

1. Log in to the NAVER Cloud Platform console.\n2. Navigate to Services > AI Services > CLOVA Speech Recognition (CSR) or AI Services > CLOVA Speech depending on your specific product.\n3. Create an Application in the console under the AI/NAVER API section (this is a mandatory step for CSR to obtain unique credentials).\n4. After creating the application, you will be issued a unique Client ID and Client Secret.\n5. You can view and manage these credentials in the application details page. Use the copy icon to retrieve them for your API headers.

2. Add them to .dlt/secrets.toml

Copy
[sources.naver_clova_speech_recognition_source]
# For CLOVA Speech Recognition (CSR) API:\nx_ncp_apigw_api_key_id = \"your_client_id_here\"\nx_ncp_apigw_api_key = \"your_client_secret_here\"\n\n# For CLOVA Speech (Long-sentence/Modern API):\nx_clovaspeech_api_key = \"your_secret_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 Naver CLOVA Speech Recognition data can I load into DuckDB?

These are the Naver CLOVA Speech Recognition endpoints dlt can load into DuckDB:

---

How do I load only new Naver CLOVA Speech Recognition records?

The Naver CLOVA Speech Recognition API reference does not document a timestamp or sequence field for these endpoints, so there is nothing to advertise here as verified. Pick a field from the endpoints table above that increases with every write, then set it as the cursor_path.

Copy
{"name": "job_status", "endpoint": {
    "path": "recognizer/results/{token}",
    # Replace with a field that increases on every write.
    "incremental": {"cursor_path": "REPLACE_ME", "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 Naver CLOVA Speech Recognition pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading For short-sentence recognition, use /recog/v1/stt. For long-sentence or external file recognition, use /recognizer/url. from the Naver CLOVA Speech Recognition API into DuckDB:

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

@dlt.source
def naver_clova_speech_recognition_source(api_key_id=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://naveropenapi.apigw.ntruss.com/recog/v1",
            "auth": {"type": "api_key", "api_key": api_key_id},
        },
        "resources": [
            {"name": "job_status", "endpoint": {"path": "recognizer/results/{token}"}},
            {"name": "long_sentence_url", "endpoint": {"path": "recognizer/url"}}
        ],
    }
    yield from rest_api_resources(config)


def load_naver_clova_speech_recognition_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="naver_clova_speech_recognition_pipeline",
        destination="duckdb",
        dataset_name="naver_clova_speech_recognition_data",
    )
    load_info = pipeline.run(naver_clova_speech_recognition_source())
    print(load_info)


if __name__ == "__main__":
    load_naver_clova_speech_recognition_to_duckdb()

Run it with python naver_clova_speech_recognition_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 Naver CLOVA Speech Recognition 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("naver_clova_speech_recognition_pipeline").dataset()
df = data.job_status.df()
print(df.head())

SQL:

Copy
SELECT * FROM naver_clova_speech_recognition_data.job_status LIMIT 10;

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

---

How do I deploy the Naver CLOVA Speech Recognition 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 Naver CLOVA Speech Recognition 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 Naver CLOVA Speech Recognition 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