[Yandex Cloud documentation](../../../index.md) > [Yandex Cloud Stackland](../../index.md) > [Step-by-step guides](../index.md) > SpeechSense > Configuring and activating

# Configuring and activating SpeechSense

Once the [images are uploaded](install-images.md), activate the SpeechSense component in the Stackland cluster.

## Getting started {#before-you-begin}

1. Make sure the SpeechSense images are [available](install-images.md) in your cluster.
1. Make sure the [NVIDIA® GPU support](../../concepts/components/gpu.md) component is enabled and the GPU nodes are available.
1. Make sure the [Managed Service for PostgreSQL](../../concepts/components/postgresql.md), [Managed Service for ClickHouse®](../../concepts/components/clickhouse.md), and [Managed Service for Apache Kafka®](../../concepts/components/kafka.md) are enabled.
1. Set up an S3-compatible storage:
    * [Create a bucket](../storage/create-bucket.md) to store audio files.
    * [Create AccessKey](../storage/create-accesskey.md) for storage access.

## Activating the component {#enable}

1. Create the `speechsense-config.yaml` manifest file:

    ```yaml
    apiVersion: stackland.yandex.cloud/v1alpha1
    kind: SpeechsenseConfig
    metadata:
      name: default
    spec:
      enabled: true
      settings:
        s3: # Optional. Add data if you need an external storage
          endpoint: "<object_storage_address>"
          accessKeyID: "<key_ID>"
          secretAccessKey: "<secret_key>"
    ```

    Where:

    * `endpoint`: Object storage address in the cluster.
    * `accessKeyID`: Storage access key ID.
    * `secretAccessKey`: Storage secret access key.

1. Apply the manifest:

    ```bash
    kubectl apply -f speechsense-config.yaml
    ```

1. Wait for the installation to complete. The controller automatically performs the following steps:

    * Creates a namespace named `stackland-speechsense`.
    * Generates secrets with database passwords.
    * Creates PostgreSQL, ClickHouse®, Apache Kafka®, and OpenSearch clusters.
    * Issues certificates via Certificate Manager.
    * Installs a Helm chart named `stackland-speechsense`.

## Checking the installation status {#check-status}

Check the component status:

```bash
kubectl get componentinstallation -n stackland-speechsense
```

Make sure all pods are running:

```bash
kubectl get pods -n stackland-speechsense
```

{% note info %}

SpeechSense installation takes time. The size of LLM images ranges from 30 to 70 GB.

{% endnote %}

## Accessing the SpeechSense console {#open-console}

Once the installation is complete, the SpeechSense console will be available at:

```text
https://speechsense.sys.$cluster.$baseDomain
```

To log in, use the Stackland user credentials. Cluster administrators automatically get the SpeechSense admin permissions.

## What's next {#whats-next}

* [Disabling SpeechSense](disable.md): Disabling SpeechSense.
* [SpeechSense](../../concepts/components/speechsense.md): Component description.