Recall AI Python API Docs | dltHub

Recall.ai is a cross-platform meeting data API that records, transcribes, and delivers meeting artifacts (recordings, transcripts, metadata) from Google Meet, Zoom, Microsoft Teams and more through a single integration. The REST API base URL is https://us-east-1.recall.ai/api/v1 and all requests require an API token in the Authorization header (Token scheme).

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv pip install "dlt[workspace]" and start loading Recall AI data in under 10 minutes.

---

What data can I load from Recall AI?

Here are some of the endpoints you can load from Recall AI:

---

How do I authenticate with the Recall AI API?

Recall.ai uses a workspace API key sent in the Authorization header as 'Authorization: Token <RECALL_API_KEY>'. For Google Meet Media flows you also supply a temporary Google OAuth access_token when creating Meeting Direct Connect sessions.

1. Get your credentials

1. Sign in to Recall.ai dashboard (https://us-west-2.recall.ai/auth/signup or Recall.ai workspace dashboard). 2) Create or select a workspace and navigate to API keys / developer settings. 3) Create or copy the workspace API token (RECALL_API_KEY). 4) For Google Meet Media API use case, create Google Cloud OAuth credentials (Client ID) and obtain Google OAuth access_token via the browser or OAuth flow as documented by Google; supply that token in the meeting_direct_connect creation payload.

2. Add them to .dlt/secrets.toml

Copy
[sources.recall_ai_google_meet_media_source]
api_key = "your_recall_api_key_here"

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
dlt ai toolkit rest-api-pipeline install

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Recall AI API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
python recall_ai_google_meet_media_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline recall_ai_google_meet_media_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset recall_ai_google_meet_media_data
The duckdb destination used duckdb:/recall_ai_google_meet_media.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
dlt pipeline recall_ai_google_meet_media_pipeline show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads meeting_direct_connect and files (Google Drive files.list) from the Recall AI API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

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

@dlt.source
def recall_ai_google_meet_media_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://us-east-1.recall.ai/api/v1",
            "auth": {
                "type": "bearer",
                "token": api_key,
            },
        },
        "resources": [
            {"name": "meeting_direct_connect", "endpoint": {"path": "meeting_direct_connect", "data_selector": "recordings"}},
            {"name": "drive_files", "endpoint": {"path": "files (drive v3: https://www.googleapis.com/drive/v3/files)", "data_selector": "files"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="recall_ai_google_meet_media_pipeline",
        destination="duckdb",
        dataset_name="recall_ai_google_meet_media_data",
    )
    load_info = pipeline.run(recall_ai_google_meet_media_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("recall_ai_google_meet_media_pipeline").dataset()
sessions_df = data.meeting_direct_connect.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM recall_ai_google_meet_media_data.meeting_direct_connect LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("recall_ai_google_meet_media_pipeline").dataset()
data.meeting_direct_connect.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Recall AI data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Troubleshooting

Authentication failures

If you receive 401 or 403 from Recall.ai endpoints, verify the Authorization header uses the Token scheme exactly: 'Authorization: Token <RECALL_API_KEY>'. For Google Drive/Meet endpoints ensure the Bearer access_token includes required scopes (drive.readonly, meetings.space.readonly).

Missing recordings or empty recordings array

If meeting_direct_connect/{id} returns recordings: [] make sure the recording_config requested a recording (e.g. video_mixed_mp4) and that someone clicked Record in the Google Meet UI (Google does not allow programmatic start of recording). Also confirm the organizer's Drive had space and appropriate permissions.

Rate limits and retries

Google Drive and Meet REST APIs enforce quotas (reads/writes limits) and will return 429 or 403 on quota exceed. Recall.ai meeting_direct_connect create endpoint base rate limit is documented as 60 requests/min per workspace; implement exponential backoff and retries.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI Workbench:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-runtime — Deploy, schedule, and monitor your pipeline in production.

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack