Ai Speech

oci.ai_speech.AIServiceSpeechClient The OCI Speech Service harnesses the power of spoken language by allowing developers to easily convert file-based data containing human speech into highly accurate text transcriptions.
oci.ai_speech.AIServiceSpeechClientCompositeOperations This class provides a wrapper around AIServiceSpeechClient and offers convenience methods for operations that would otherwise need to be chained together.

Models

oci.ai_speech.models.AudioFormatDetails Audio format details.
oci.ai_speech.models.ChangeCustomizationCompartmentDetails Details for changing the compartment of a Customization.
oci.ai_speech.models.ChangeTranscriptionJobCompartmentDetails Details for changing the compartment of a transcription job.
oci.ai_speech.models.CreateCustomizationDetails The information about the new Customization.
oci.ai_speech.models.CreateRealtimeSessionTokenDetails Request sent to the realtime authentication endpoint in order to obtain the auth token.
oci.ai_speech.models.CreateTranscriptionJobDetails The information about new Transcription Job.
oci.ai_speech.models.Customization Description of a Customization.
oci.ai_speech.models.CustomizationCollection Results of a Customization search.
oci.ai_speech.models.CustomizationDatasetDetails Customization Training Dataset
oci.ai_speech.models.CustomizationInference Inference payload for using Customization in Realtime Speech or Async Speech
oci.ai_speech.models.CustomizationInferenceEntity Entity Object for customization inference payload
oci.ai_speech.models.CustomizationModelDetails Customization details.
oci.ai_speech.models.CustomizationReferencedEntities Entities referenced by top level customization.
oci.ai_speech.models.CustomizationSummary Summary of the Customization.
oci.ai_speech.models.Diarization Speaker diarization is a combination of speaker segmentation and speaker clustering.
oci.ai_speech.models.Entity Entity Object Reference
oci.ai_speech.models.EntityList List of entities of a given type, to be used to train a customization.
oci.ai_speech.models.EntityListDataset Entity List Dataset
oci.ai_speech.models.InputLocation The location of the input(s).
oci.ai_speech.models.LocationDetails Possible object storage location types
oci.ai_speech.models.ObjectListDataset Data source details for object storage
oci.ai_speech.models.ObjectListFileInputLocation Use this locationType when passing the location of the object storage in the request (where the WAV file is stored).
oci.ai_speech.models.ObjectListInlineInputLocation Use this locationType when passing the WAV file name in the request.
oci.ai_speech.models.ObjectLocation A location in Object Storage that is uniquely identified by namespace name, bucket name and object name.
oci.ai_speech.models.ObjectStorageDataset Object Storage Dataset
oci.ai_speech.models.OutputLocation OCI Object Storage Location.
oci.ai_speech.models.ProfanityTranscriptionFilter Profanity transcription filter to recognize profane words.
oci.ai_speech.models.Pronunciation Pronunciation Object Reference
oci.ai_speech.models.RealtimeMessage Websocket messages sent between client and service.
oci.ai_speech.models.RealtimeMessageAckAudio The websocket ack message received from service.
oci.ai_speech.models.RealtimeMessageAckAudioDetails Details object for the websocket ack message received from service.
oci.ai_speech.models.RealtimeMessageAuthentication The payload for authentication.
oci.ai_speech.models.RealtimeMessageAuthenticationCredentials The payload for credential-based authentication.
oci.ai_speech.models.RealtimeMessageAuthenticationToken The payload for JWT based authentication.
oci.ai_speech.models.RealtimeMessageConnect The websocket connection message received from service.
oci.ai_speech.models.RealtimeMessageError The websocket error message received from service.
oci.ai_speech.models.RealtimeMessageOut Websocket messages sent by client to the service.
oci.ai_speech.models.RealtimeMessageResult The websocket result message received from service.
oci.ai_speech.models.RealtimeMessageResultTranscription Transcription object.
oci.ai_speech.models.RealtimeMessageResultTranscriptionToken Individual transcription tokens.
oci.ai_speech.models.RealtimeMessageSendFinalResult Tell service to send final result
oci.ai_speech.models.RealtimeModelDetails Details of the ASR model used by the realtime speech service.
oci.ai_speech.models.RealtimeParameters Parameters to be sent to the realtime speech service over a websocket connection.
oci.ai_speech.models.RealtimeSessionToken The response from the realtime session token endpoint that creates the auth token to be used with the realtime speech service.
oci.ai_speech.models.SynthesizeSpeechDetails Input JSON to get audio inference from TTS Service.
oci.ai_speech.models.TranscriptionFilter Transcription Filter.
oci.ai_speech.models.TranscriptionJob Description of Transcription Job.
oci.ai_speech.models.TranscriptionJobCollection Results of a Transcription Job search.
oci.ai_speech.models.TranscriptionJobSummary Summary of the Transcription Job.
oci.ai_speech.models.TranscriptionModelDetails Model details.
oci.ai_speech.models.TranscriptionNormalization Information to Normalize generated transcript.
oci.ai_speech.models.TranscriptionSettings Processes to perform on the generated transcription.
oci.ai_speech.models.TranscriptionTask Description of Transcription Task.
oci.ai_speech.models.TranscriptionTaskCollection Results of a Transcription Task search.
oci.ai_speech.models.TranscriptionTaskSummary Summary of the Transcription Task.
oci.ai_speech.models.TtsAudioConfig Use this schema to specify handling of audio response.
oci.ai_speech.models.TtsBaseAudioConfig Use this audio config for saving the audio response at specified path.
oci.ai_speech.models.TtsConfiguration Speech configuration for TTS API.
oci.ai_speech.models.TtsOracleConfiguration Use this configuration for selecting a model from Oracle model family.
oci.ai_speech.models.TtsOracleModelDetails Model specific properties to use with Oracle model for TTS.
oci.ai_speech.models.TtsOracleSpeechSettings Settings to use for generating speech with a model from ORACLE family.
oci.ai_speech.models.TtsOracleTts1StandardModelDetails Use this schema for specifying properties of TTS_1_STANDARD model from Oracle model family.
oci.ai_speech.models.TtsOracleTts2NaturalModelDetails Use this schema for specifying properties of TTS_2_NATURAL model from Oracle model family.
oci.ai_speech.models.UpdateCustomizationDetails The information to be updated.
oci.ai_speech.models.UpdateTranscriptionJobDetails The information to be updated.
oci.ai_speech.models.VoiceCollection Results of the voices available as speaker Ids for given language code and voice type combination.
oci.ai_speech.models.VoiceSummary Details related to the voice available for the given language code and voice type.