| Name | Type | Description |
|---|---|---|
project_id* | str | Google Cloud Project ID. |
file_path* | str | Google Cloud Storage URI or local file path. |
location | str | Default: 'us-central1'Speech-to-Text recognizer location. |
recognizer_id | str | Default: '_' |
config | Optional[RecognitionConfig] | Default: None |
config_mask | Optional[FieldMask] | Default: None |
is_long | bool | Default: False |
Loader for Google Cloud Speech-to-Text audio transcripts.
Inherits from BaseLoader.
Transcribes audio files using Google Cloud Speech-to-Text API and loads transcribed text into documents. Supports both GCS URIs and local file paths.
See Speech-to-Text documentation for detailed information.
Requires additional dependencies:
pip install langchain-google-community[speech]Speech-to-Text recognizer ID.
Recognition options and features. See
RecognitionConfig.
Fields in config that override default_recognition_config
of the recognizer. See RecognizeRequest.
Use async Cloud Speech recognition for long audio files. See batch recognize.