> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pipecat.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickdial

> Speech-to-text service implementation using Quickdial's whisper.cpp transcription API

export const CommunityMaintained = ({maintainer, maintainerUrl, repo}) => <Note>
    <strong>Community-maintained integration.</strong> This service is built and
    maintained by{" "}
    <a href={maintainerUrl} target="_blank" rel="noreferrer">
      {maintainer}
    </a>
    . Pipecat does not test or officially support it. Please report issues and
    request changes on the{" "}
    <a href={repo} target="_blank" rel="noreferrer">
      source repository
    </a>
    . Learn more about{" "}
    <a href="/api-reference/server/services/community-integrations">
      community integrations
    </a>
    .
  </Note>;

<CommunityMaintained maintainer="Quickdial AI" maintainerUrl="https://github.com/samay-ai" repo="https://github.com/samay-ai/pipecat-quickdial" />

## Overview

`QuickdialSTTService` transcribes speech to text using [Quickdial](https://quickdial.ai/)'s
speech-to-text API (powered by whisper.cpp). It extends Pipecat's
`SegmentedSTTService`: an upstream VAD segments speech into utterances, each of
which is transcribed and pushed downstream as a `TranscriptionFrame`.

<CardGroup cols={2}>
  <Card title="Source Repository" icon="github" href="https://github.com/samay-ai/pipecat-quickdial">
    Source code, examples, and issues for the Quickdial integration
  </Card>

  <Card title="PyPI Package" icon="cube" href="https://pypi.org/project/pipecat-quickdial/">
    The `pipecat-quickdial` package on PyPI
  </Card>

  <Card title="Quickdial" icon="book" href="https://quickdial.ai/">
    Learn more about Quickdial and get an API key
  </Card>

  <Card title="Docs" icon="file-lines" href="https://quickdial.ai/docs">
    Quickdial API reference (REST + WebSocket)
  </Card>
</CardGroup>

## Installation

This is a community-maintained package distributed separately from `pipecat-ai`:

```bash theme={null}
uv add pipecat-quickdial
```

## Prerequisites

1. **Quickdial account** — sign up at [web.quickdial.ai](https://web.quickdial.ai) (1000 free credits, no card required).
2. **API key** — create one in the dashboard.

### Required environment variables

```bash theme={null}
QUICKDIAL_API_KEY=qtts_live_your_key
```

## Configuration

| Parameter     | Type   | Default                     | Description                                     |
| ------------- | ------ | --------------------------- | ----------------------------------------------- |
| `api_key`     | `str`  | `QUICKDIAL_API_KEY` env var | Your Quickdial API key.                         |
| `language`    | `str`  | `"en"`                      | Transcription language.                         |
| `base_url`    | `str`  | `https://api.quickdial.ai`  | API base URL.                                   |
| `sample_rate` | `int`  | pipeline default            | Input sample rate (Hz).                         |
| `params`      | `dict` | `None`                      | Optional model knobs passed through to the API. |

## Usage

```python theme={null}
import os

from pipecat_quickdial import QuickdialSTTService

stt = QuickdialSTTService(
    api_key=os.getenv("QUICKDIAL_API_KEY"),
    language="en",
)

# ...add `stt` to your Pipecat Pipeline([...]) (with a VAD upstream)
```

## Additional resources

* [pipecat-quickdial on GitHub](https://github.com/samay-ai/pipecat-quickdial) — source, example, and issues
* [Quickdial API docs](https://quickdial.ai/docs)