Speechmatics Python API Docs | dltHub

Speechmatics is a speech-to-text and Voice AI platform providing REST and WebSocket APIs for batch transcription, real-time (realtime) transcription, and Flow Voice AI agents. The REST API base URL is Batch/Jobs REST: https://{region}.asr.api.speechmatics.com/v2 (examples: https://eu1.asr.api.speechmatics.com/v2) Realtime (websocket) base: wss://{region}.rt.speechmatics.com/v2 Flow Voice AI websocket base: wss://flow.api.speechmatics.com/ and all requests require a Bearer API key (or temporary JWT) for authentication..

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 Speechmatics data in under 10 minutes.

---

What data can I load from Speechmatics?

Here are some of the endpoints you can load from Speechmatics:

---

How do I authenticate with the Speechmatics API?

Long-lived API keys are supplied in the Authorization header as: Authorization: Bearer <API_KEY>. Temporary keys (JWTs) can be created and used in place of the API key for short-lived client or browser access and may be passed in the Authorization header or as a query parameter for WebSocket connections.

1. Get your credentials

1. Sign in to the Speechmatics Portal (https://portal.speechmatics.com). 2. Go to Settings -> API Keys. 3. Create a new API key (name it, choose type if prompted) and copy the key_value. Store securely. 4. Optionally create temporary keys via the management endpoint (POST https://mp.speechmatics.com/v1/api_keys?type=batch or ?type=rt) using your long-lived key.

2. Add them to .dlt/secrets.toml

Copy
[sources.speechmatics_flow_voice_ai_source]
api_key = "your_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 Speechmatics 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 speechmatics_flow_voice_ai_pipeline.py

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

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

Inspect your pipeline and data:

Copy
dlt pipeline speechmatics_flow_voice_ai_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 batch_jobs and models from the Speechmatics 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 speechmatics_flow_voice_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "Batch/Jobs REST: https://{region}.asr.api.speechmatics.com/v2 (examples: https://eu1.asr.api.speechmatics.com/v2) Realtime (websocket) base: wss://{region}.rt.speechmatics.com/v2 Flow Voice AI websocket base: wss://flow.api.speechmatics.com/",
            "auth": {
                "type": "bearer",
                "api_key": api_key,
            },
        },
        "resources": [
            {"name": "batch_jobs", "endpoint": {"path": "v2/jobs/", "data_selector": "jobs"}},
            {"name": "models", "endpoint": {"path": "v2/models/", "data_selector": "models"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="speechmatics_flow_voice_ai_pipeline",
        destination="duckdb",
        dataset_name="speechmatics_flow_voice_ai_data",
    )
    load_info = pipeline.run(speechmatics_flow_voice_ai_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("speechmatics_flow_voice_ai_pipeline").dataset()
sessions_df = data.batch_jobs.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM speechmatics_flow_voice_ai_data.batch_jobs LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("speechmatics_flow_voice_ai_pipeline").dataset()
data.batch_jobs.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 Speechmatics 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

Requests without a valid region-scoped API key return HTTP 401 Unauthorized. Ensure you use the API key for the region your account is provisioned in (e.g., eu1) and include the header: Authorization: Bearer <API_KEY>.

Temporary key / permissions issues

Temporary keys created without appropriate client_ref may be restricted (403) from accessing some endpoints (e.g., Usage). Use the correct token type (batch vs rt) and include client_ref when exposing tokens to end users.

Rate limits and wrong region

The docs indicate region-specific endpoints; using the wrong regional host will yield authorization or 401 errors. Follow retry/backoff on transient errors and confirm region in your Portal/API key settings.

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