Haystack Audio API Python API Docs | dltHub

Haystack Audio API is the audio transcription components in the Haystack library (LocalWhisperTranscriber and RemoteWhisperTranscriber) that transcribe audio into documents using local Whisper models or the OpenAI Whisper API. The REST API base URL is `` and Remote transcription requires an OpenAI API key; Local transcription runs locally and needs no external auth..

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 Haystack Audio API data in under 10 minutes.

---

What data can I load from Haystack Audio API?

Here are some of the endpoints you can load from Haystack Audio API:

---

How do I authenticate with the Haystack Audio API API?

RemoteWhisperTranscriber requires an OpenAI API key provided via environment variable OPENAI_API_KEY or passed as the 'api_key' parameter; the component forwards requests to OpenAI which uses Bearer token auth in the Authorization header.

1. Get your credentials

1. Sign in to your OpenAI account at https://platform.openai.com/. 2) Go to 'View API keys' or 'API keys' in the user menu. 3) Create a new secret key and copy it. 4) Store it securely; set environment variable OPENAI_API_KEY with the key or pass it to RemoteWhisperTranscriber as Secret.from_env_var('OPENAI_API_KEY').

2. Add them to .dlt/secrets.toml

Copy
[sources.haystack_audio_api_source]
api_key = "your_openai_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 Haystack Audio API 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 haystack_audio_api_pipeline.py

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

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

Inspect your pipeline and data:

Copy
dlt pipeline haystack_audio_api_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 local_whisper_transcriptions and remote_whisper_transcriptions from the Haystack Audio API 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 haystack_audio_api_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "",
            "auth": {
                "type": "bearer",
                "api_key": api_key,
            },
        },
        "resources": [
            {"name": "local_whisper_transcriptions", "endpoint": {"path": "(library) LocalWhisperTranscriber.run", "data_selector": "documents"}},
            {"name": "remote_whisper_transcriptions", "endpoint": {"path": "(library) RemoteWhisperTranscriber.run -> OpenAI /v1/audio/transcriptions", "data_selector": "documents"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="haystack_audio_api_pipeline",
        destination="duckdb",
        dataset_name="haystack_audio_api_data",
    )
    load_info = pipeline.run(haystack_audio_api_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("haystack_audio_api_pipeline").dataset()
sessions_df = data.local_whisper_transcriptions.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM haystack_audio_api_data.local_whisper_transcriptions LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("haystack_audio_api_pipeline").dataset()
data.local_whisper_transcriptions.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 Haystack Audio API 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 RemoteWhisperTranscriber cannot authenticate, ensure OPENAI_API_KEY is set or the api_key parameter is provided. OpenAI returns 401 for invalid/missing keys.

Rate limits and OpenAI errors

Remote transcriptions call the OpenAI API and are subject to OpenAI rate limits and quota; errors will surface as 429 (rate limit) or 402/403 depending on billing/permissions. Handle retries/backoff.

Invalid audio or format errors

Local and remote transcribers expect supported audio formats (see Whisper/OpenAI docs). Invalid formats or corrupt files cause processing errors; check exceptions from the component or the OpenAI error response.

No Haystack Audio REST endpoints

Haystack audio is exposed as Python components and not as a public REST API. There is no base REST URL to query for 'audio' resources; treat it as a library integration calling OpenAI for remote transcription.

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