Ai Speech¶
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. |
|
This class provides a wrapper around |
Models¶
Audio format details. |
|
Details for changing the compartment of a Customization. |
|
|
Details for changing the compartment of a transcription job. |
The information about the new Customization. |
|
Request sent to the realtime authentication endpoint in order to obtain the auth token. |
|
The information about new Transcription Job. |
|
Description of a Customization. |
|
Results of a Customization search. |
|
Customization Training Dataset |
|
Inference payload for using Customization in Realtime Speech or Async Speech |
|
Entity Object for customization inference payload |
|
Details of the base ASR model to train a Customization for. |
|
Entities referenced by top level customization. |
|
Summary of the Customization. |
|
Speaker diarization is a combination of speaker segmentation and speaker clustering. |
|
Entity Object Reference |
|
List of entities of a given type, to be used to train a customization. |
|
Entity List Dataset |
|
The location of the input(s). |
|
Possible object storage location types |
|
Data source details for object storage |
|
Use this locationType when passing the location of the object storage in the request (where the WAV file is stored). |
|
Use this locationType when passing the WAV file name in the request. |
|
A location in Object Storage that is uniquely identified by namespace name, bucket name and object name. |
|
Object Storage Dataset |
|
OCI Object Storage Location. |
|
Profanity transcription filter to recognize profane words. |
|
Pronunciation Object Reference |
|
Websocket messages sent between client and service. |
|
The websocket ack message received from service. |
|
Details object for the websocket ack message received from service. |
|
The payload for authentication. |
|
|
The payload for credential-based authentication. |
The payload for JWT based authentication. |
|
The websocket connection message received from service. |
|
The websocket error message received from service. |
|
Websocket messages sent by client to the service. |
|
The websocket result message received from service. |
|
Transcription object. |
|
|
Individual transcription tokens. |
Tell service to send final result |
|
Details of the ASR model used by the realtime speech service. |
|
Parameters to be sent to the realtime speech service over a websocket connection. |
|
The response from the realtime session token endpoint that creates the auth token to be used with the realtime speech service. |
|
Input JSON to get audio inference from TTS Service. |
|
Transcription Filter. |
|
Description of Transcription Job. |
|
Results of a Transcription Job search. |
|
Summary of the Transcription Job. |
|
Model details. |
|
Information to Normalize generated transcript. |
|
Processes to perform on the generated transcription. |
|
Description of Transcription Task. |
|
Results of a Transcription Task search. |
|
Summary of the Transcription Task. |
|
Use this schema to specify handling of audio response. |
|
Use this audio config for saving the audio response at specified path. |
|
Speech configuration for TTS API. |
|
Use this configuration for selecting a model from Oracle model family. |
|
Model specific properties to use with Oracle model for TTS. |
|
Settings to use for generating speech with a model from ORACLE family. |
|
Use this schema for specifying properties of TTS_1_STANDARD model from Oracle model family. |
|
Use this schema for specifying properties of TTS_2_NATURAL model from Oracle model family. |
|
The information to be updated. |
|
The information to be updated. |
|
Results of the voices available as speaker Ids for given language code and voice type combination. |
|
Details related to the voice available for the given language code and voice type. |