Class SpeechToTextConfig (2.52.0) 

SpeechToTextConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Configures speech transcription for ConversationProfile.

Attributes
Name Description
speech_model_variant google.cloud.dialogflow_v2.types.SpeechModelVariant
The speech model used in speech to text. SPEECH_MODEL_VARIANT_UNSPECIFIED, USE_BEST_AVAILABLE will be treated as USE_ENHANCED. It can be overridden in AnalyzeContentRequest and StreamingAnalyzeContentRequest request. If enhanced model variant is specified and an enhanced version of the specified model for the language does not exist, then it would emit an error.
model str
Which Speech model to select. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then Dialogflow auto-selects a model based on other parameters in the SpeechToTextConfig and Agent settings. If enhanced speech model is enabled for the agent and an enhanced version of the specified model for the language does not exist, then the speech is recognized using the standard version of the specified model. Refer to `Cloud Speech API documentation
phrase_sets MutableSequence[str]
List of names of Cloud Speech phrase sets that are used for transcription. For phrase set limitations, please refer to `Cloud Speech API quotas and limits
audio_encoding google.cloud.dialogflow_v2.types.AudioEncoding
Audio encoding of the audio content to process.
sample_rate_hertz int
Sample rate (in Hertz) of the audio content sent in the query. Refer to `Cloud Speech API documentation
language_code str
The language of the supplied audio. Dialogflow does not do translations. See `Language Support
enable_word_info bool
If true, Dialogflow returns SpeechWordInfo in StreamingRecognitionResult with information about the recognized speech words, e.g. start and end time offsets. If false or unspecified, Speech doesn't return any word-level information.
use_timeout_based_endpointing bool
Use timeout based endpointing, interpreting endpointer sensitivity as seconds of timeout value.
gemini_asr_config google.cloud.dialogflow_v2.types.SpeechToTextConfig.GeminiAsrConfig
Optional. Configuration for using Gemini ASR models served via Vertex AI, overriding the default Gemini ASR model or providing additional advanced parameters. This field is only used when use_gemini_asr is true.
use_gemini_asr bool
Optional. If true, Gemini ASR will be used for transcription instead of Cloud Speech-to-Text.

Classes

GeminiAsrConfig

GeminiAsrConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Configuration for using Gemini ASR models served via Vertex AI. This message is used to override the default Gemini ASR model or provide additional advanced parameters.