×

Recognizer

 
A set of methods for voice recognition.
 
Call
Description
RecognizeStreaming
Expects audio in real-time
 
CALLS RECOGNIZER
RECOGNIZESTREAMING
 
Expects audio in real-time
 
rpc RecognizeStreaming (stream StreamingRequest) returns (stream StreamingResponse)
 
StreamingRequest
Field
Description
 Event
oneof: session_options, chunk, silence_chunk or eou
  session_options
StreamingOptions
Session options. Should be the first message from user.
   chunk
AudioChunk
Chunk with audio data.
   silence_chunk
SilenceChunk
Chunk with silence.
   eou
Eou
Request to end current utterance. Works only with external EOU detector.
 
StreamingOptions
Field
Description
 recognition_model
RecognitionModelOptions
Configuration for speech recognition model.
 eou_classifier
EouClassifierOptions
Configuration for end of utterance detection model.
 recognition_classifier
RecognitionClassifierOptions
Configuration for classifiers over speech recognition.
 speech_analysis
SpeechAnalysisOptions
Configuration for speech analysis over speech recognition.
 speaker_labeling
Configuration for speaker labeling
 
RecognitionModelOptions
Field
Description
 model
string
Sets the recognition model for the cloud version of SpeechKit. Possible values: 'general', 'general:rc', 'general:deprecated'. The model is ignored for SpeechKit Hybrid.
 audio_format
AudioFormatOptions
Specified input audio.
 text_normalization
TextNormalizationOptions
Text normalization options.
 language_restriction
LanguageRestrictionOptions
Possible languages in audio.
 audio_processing_type
enum AudioProcessingType
How to deal with audio data (in real time, after all data is received, etc). Default is REAL_TIME.
  • REAL_TIME: Process audio in mode optimized for real-time recognition, i.e. send partials and final responses as soon as possible
  • FULL_DATA: Process audio after all data was received
 
AudioFormatOptions
Field
Description
 AudioFormat
oneof: raw_audio or container_audio
 
  raw_audio
RawAudio
Audio without container.
   container_audio
ContainerAudio
Audio is wrapped in container.