> [!WARNING]
>
> **Preview**
>
>
> This product or feature is
>
> subject to the "Pre-GA Offerings Terms" in the General Service Terms section
> of the [Service Specific
> Terms](https://docs.cloud.google.com/terms/service-terms#1).
>
> Pre-GA products and features are available "as is" and might have limited support.
>
> For more information, see the
> [launch stage descriptions](https://cloud.google.com/products/#product-launch-stages).

In Cloud Speech-to-Text API V2, there are different availabilities in different regions.
To understand the availabilities, use the Locations API.

## Location Metadata

Each location returned by the Locations API has metadata associated with it that
details the languages, models, and model features that are available. A sample
location with its metadata is shown below.

```json
{
  "locationId": "europe-west1",
  "metadata": {
    "languages": {
      "models": {
        "es-ES": {
          "modelFeatures": {
            "latest_long": {
              "modelFeature": [
                {"feature": "profanity_filter", "releaseState": "GA"},
                {"feature": "spoken_punctuation", "releaseState": "GA"},
                {"feature": "automatic_punctuation", "releaseState": "GA"},
                {"feature": "speaker_diarization", "releaseState": "PREVIEW_DIARIZATION"},
              ]
            }
          }
        }
      }
    }
  }
}
```

## Filtering in List Locations

When listing all availabilities, a filter can be used. The different criteria
that can be used to filter are the following:

- `language` Optional. The BCP-47 language tag of the language desired.
- `model` Optional. The model desired.
- `model_feature` Optional. The model feature desired.

A sample filter query is shown below. Please see
[filter syntax](https://google.aip.dev/160) for further reference.

```json
"language = en-US AND model = latest_long AND model_feature != profanity_filter"
```