> ## 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.

# Alkove VAD

> AlkoveVADAnalyzer implements Pipecat's VADAnalyzer interface with Alkove's Cue model, on the bot's CPU

> [!NOTE]
>
> **Community-maintained integration.** This service is built and
> maintained by
> [edbrdi](https://github.com/edbrdi)
> . Pipecat does not test or officially support it. Please report issues and
> request changes on the
> [source repository](https://github.com/alkove-ai/alkove/tree/main/integrations/pipecat)
> . Learn more about
> [community integrations](https://docs.pipecat.ai/api-reference/server/services/community-integrations.md)
> .

## Overview

`AlkoveVADAnalyzer` is a Pipecat `VADAnalyzer` implementation backed by Cue,
the speech detection model of [Alkove](https://alkove.ai), an open-source
(Apache-2.0) voice SDK. It gives a speech probability every 30 ms, at any input
rate, and is a drop-in alternative to Pipecat's built-in `SileroVADAnalyzer`.
It runs locally on the CPU with Alkove's own inference engine: no API key and
no network calls after the model download.

Behind [`AlkoveFilter`](https://docs.pipecat.ai/api-reference/server/services/audio-filters/alkove),
which removes the other voices and the noise, it hears only the user.

> [card] [Source Repository](https://github.com/alkove-ai/alkove/tree/main/integrations/pipecat)
>
> Code, example and README of the Pipecat plugin

> [card] [PyPI Package](https://pypi.org/project/pipecat-alkove/)
>
> The `pipecat-alkove` package on PyPI

## Installation

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

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

## Prerequisites

* **No API key.** The models (Focus 1.1 MB, Cue 1.1 MB) download once into the
  cache and are checked by their sha256, when the analyzer is created.

## Configuration

**params** `VADParams | None` (default: VADParams(confidence=0.5))

Pipecat's VAD parameters. Cue was tuned with a confidence of 0.5, so that is
its default; the other values stay Pipecat's (`stop_secs` 0.2 s, for Smart
Turn).

**sample\_rate** `int | None` (default: None)

Input sample rate. `None` takes the transport's.

**models** `alkove.Models | None` (default: None)

Models to use. `None` loads Focus and Cue once per process, shared by every
session.

## Usage

Give the analyzer to your user aggregator, as you would Silero's:

```python theme={null}
from pipecat.processors.aggregators.llm_response_universal import LLMUserAggregatorParams
from pipecat.transports.base_transport import TransportParams
from pipecat_alkove import AlkoveFilter, AlkoveVADAnalyzer

transport_params = TransportParams(audio_in_enabled=True, audio_in_filter=AlkoveFilter())
user_params = LLMUserAggregatorParams(vad_analyzer=AlkoveVADAnalyzer())
```

It also works in a `VADProcessor`;
[example.py](https://github.com/alkove-ai/alkove/blob/main/integrations/pipecat/example.py)
runs it on your microphone and prints when you speak.

## Compatibility

Tested with Pipecat 1.14.0. See the
[changelog](https://github.com/alkove-ai/alkove/blob/main/CHANGELOG.md) for the
latest version.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.