Vast.ai Whisper ASR Python API Docs | dltHub

Vast.ai Whisper ASR is a speech recognition service that provides language detection and transcription via a REST API. The REST API base URL is https://cloud.vast.ai/api/ and All requests require a Bearer token passed in the Authorization header..

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 Vast.ai Whisper ASR data in under 10 minutes.

---

What data can I load from Vast.ai Whisper ASR?

Here are some of the endpoints you can load from Vast.ai Whisper ASR:

---

How do I authenticate with the Vast.ai Whisper ASR API?

Authentication uses the OPEN_BUTTON_TOKEN as a Bearer token; include it in the request header Authorization: Bearer <OPEN_BUTTON_TOKEN>.

1. Get your credentials

1. Log in to your Vast.ai account.
2. Navigate to the user dashboard or account settings.
3. Locate the section titled "API Tokens" or "Open Button Token".
4. Click "Create" or "Reveal" to generate/view the token.
5. Copy the token value; this is the OPEN_BUTTON_TOKEN you will use for authentication.

2. Add them to .dlt/secrets.toml

Copy
[sources.vast_ai_whisper_asr_source]
token = "<OPEN_BUTTON_TOKEN>"

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 Vast.ai Whisper ASR 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 vast_ai_whisper_asr_pipeline.py

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

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

Inspect your pipeline and data:

Copy
dlt pipeline vast_ai_whisper_asr_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 detect-language and asr from the Vast.ai Whisper ASR 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 vast_ai_whisper_asr_source(token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://cloud.vast.ai/api/",
            "auth": {
                "type": "bearer",
                "token": token,
            },
        },
        "resources": [
            {"name": "detect_language", "endpoint": {"path": "detect-language"}},
            {"name": "asr", "endpoint": {"path": "asr"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="vast_ai_whisper_asr_pipeline",
        destination="duckdb",
        dataset_name="vast_ai_whisper_asr_data",
    )
    load_info = pipeline.run(vast_ai_whisper_asr_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("vast_ai_whisper_asr_pipeline").dataset()
sessions_df = data.detect_language.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM vast_ai_whisper_asr_data.detect_language LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("vast_ai_whisper_asr_pipeline").dataset()
data.detect_language.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 Vast.ai Whisper ASR 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 Errors

• 401 Unauthorized – Occurs when the OPEN_BUTTON_TOKEN is missing, malformed, or expired. Ensure the token is correct and included as Authorization: Bearer <token>.

Large File Uploads

• 500 Internal Server Error – The guide notes that uploading a file that is too large can trigger this error. Reduce the file size or split the audio into smaller chunks before uploading.

Rate Limiting

• 429 Too Many Requests – If you exceed the platform’s request quota, the API will respond with a 429 status. Implement exponential back‑off and respect the Retry-After header when present.

Session Loss

• Closing the browser may cause loss of access to an ongoing session, as indicated in the integration notes. Keep the session active or re‑authenticate if the session is terminated.

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