The "latest" model tags in the Cloud Speech-to-Text API give access to two new model tags
that can be used when you specify the model field. These models are designed to
give you access to the latest speech technology and machine learning research
from Google, and can provide higher accuracy for speech recognition over other
available models. However, some features that are supported by other available
models are not yet supported by the "latest" models.

The latest models are based on the Conformer Speech Model technology from
Google. To find out more, see [Google Research
Publications](https://research.google/pubs/).

Using the latest models requires a general understanding of using the
Cloud Speech-to-Text API or UI.

### Model identifiers

The latest models are available in two different versions:

- The `latest_short` model is for short utterances that are a few seconds in
  length. It is useful for trying to capture commands or other single shot
  directed speech use cases. Consider using `latest_short` instead of the
  `command_and_search` model.

- The `latest_long` model is for any kind of long form content such as media
  or spontaneous speech and conversations. Consider using `latest_long` in
  place of `video`, especially if `video` is not available in your target
  language. You can also use `latest_long` in place of the `default` model.

### Model technology

The goal of the latest models is to bring the latest in speech technology
directly to Google Cloud users. Our current Latest models are based on the
Conformer Speech Model technology from Google, but this may change in the
future. To find out more, check out [Google Research
Publications](https://research.google/pubs/) list.

### Pricing

The `latest_long` and `latest_short` models are billed as "Standard" and subject
to the same usage and costs as the `command_and_search` or `default` models. For
more information, see [Pricing](https://docs.cloud.google.com/speech-to-text/pricing).

### Model updates

Latest models are based on rapidly advancing machine learning technology. For
this reason we might perform model updates or refreshes more frequently than on
our other models. These updates can add additional features or make slight
changes to accuracy or latency.

### Languages

Latest models are available in more than 20 languages and more than 50 variants.
We are always adding languages, so refer to
[Languages](https://docs.cloud.google.com/speech-to-text/docs/v1/speech-to-text-supported-languages) for the most up
to date list.

### Feature Support and Limitations

Feature support varies by language. See
[Languages](https://docs.cloud.google.com/speech-to-text/docs/v1/speech-to-text-supported-languages) for a full list
of supported features.

The latest models don't support the following feature:

- **Confidence scores** - The API will return a value, but it is not truly a confidence score.

### Model Service Level Agreement

The latest models are considered a Generally Available part of the Cloud Speech-to-Text API.
As such the functionality they support is available in the V1 API and eligible
for the same Service Level Agreement and other protections afforded to Generally
Available products and features.