Recognizes speech in audio input and translates it.

View on GitHub

Last Updated: Feb. 25, 2023

Access Instructions

Install the Google provider package into your Airflow environment.

Import the module into your DAG file and instantiate it with your desired params.


audioRequiredaudio data to be recognized. See more:
configRequiredinformation to the recognizer that specifies how to process the request. See more:
target_languageRequiredThe language to translate results into. This is required by the API and defaults to the target language of the current instance. Check the list of available languages here:
format_Required(Optional) One of text or html, to specify if the input text is plain text or HTML.
source_languageRequired(Optional) The language of the text to be translated.
modelRequired(Optional) The model used to translate the text, such as 'base' or 'nmt'.
project_idOptional, Google Cloud Project ID where the Compute Engine Instance exists. If set to None or missing, the default project_id from the Google Cloud connection is used.
gcp_conn_idOptional, The connection ID used to connect to Google Cloud. Defaults to ‘google_cloud_default’.
impersonation_chainOptional service account to impersonate using short-term credentials, or chained list of accounts required to get the access_token of the last account in the list, which will be impersonated in the request. If set as a string, the account must grant the originating account the Service Account Token Creator IAM role. If set as a sequence, the identities from the list must grant Service Account Token Creator IAM role to the directly preceding identity, with first account from the list granting this role to the originating account (templated).


Recognizes speech in audio input and translates it.

Note that it uses the first result from the recognition api response - the one with the highest confidence In order to see other possible results please use CloudSpeechToTextRecognizeSpeechOperator and CloudTranslateTextOperator separately

See also

For more information on how to use this operator, take a look at the guide: CloudTranslateSpeechOperator


Execute method returns string object with the translation

This is a list of dictionaries queried value. Dictionary typically contains three keys (though not all will be present in all cases).

  • detectedSourceLanguage: The detected language (as an ISO 639-1 language code) of the text.

  • translatedText: The translation of the text into the target language.

  • input: The corresponding input value.

  • model: The model used to translate the text.

Dictionary is set as XCom return value.

Was this page helpful?