This sub-page helps the integrator to understand two different types of request payload, one without any additional configuration parameters, and one with additional configuration parameters.
We will now understand about each parameter available as a part of this payload.
taskType
Type: String
Line 3-5 for ASR
Line 6-8 for Translation
Line 9-11 for TTS
pipelineTasks
pipelineId
Type: String
pipelineId takes a string value of the specific pipeline integrator wants to use. The pipeline ID can be obtained either via Pipeline Search Call or via ULCA Web based on the description which helps the integrator to understand what a pipeline can or cannot do.
Each pipeline ID may support multiple task and task sequences.
pipelineRequestConfig
Integrators want to do individual tasks
pipelineTasksarray takes only one dictionary with taskType as asr
"pipelineTasks" : [
{
"taskType" : "asr"
}
]
pipelineTasksarray takes only one dictionary with taskType as translation
pipelineTasksarray takes only one dictionary with taskType as tts
"pipelineTasks" : [
{
"taskType" : "tts"
}
]
Integrators want to do combination of tasks in that order
pipelineTasksarray takes two dictionaries with taskType as asr and translation in that sequence.
Requesting Server with this in the pipelineTasks parameter would mean that integrator wants to ask the server to give the configuration details where server will be able to perform ASR and Translation together by first doing ASR on the input audio, generating digital text of that audio and then also able to generate translation on the output of that ASR.
pipelineTasksarray takes two dictionaries with taskType as translation and tts in that sequence.
Requesting Server with this in the pipelineTasks parameter would mean that integrator wants to ask the server to give the configuration details where server will be able to perform Translation and TTS together by first doing Translation on the input text, generating translated text in another language and then also able to generate Speech on the output of that translation.
pipelineTasksarray takes three dictionaries with taskType as asr, translation and tts in that sequence.
Requesting Server with this in the pipelineTasks parameter would mean that integrator wants to ask the server to give the configuration details where server will be able to perform ASR, Translation and TTS together by first performing ASR, thereby generating digital text from the input audio, then doing Translation on the output of previous ASR, thereby generating digital text in another language and finally doing TTS on the output of previous Translation, thereby generating Speech in the required language.
Only additional parameter config is detailed out below. Rest of the parameters' understanding remains the same as Without Configuration Parameters.
config
Type: dictionary
config parameter is used for sending configuration parameters to the server for each taskType. Each taskType may have some common parameters such as language and some parameters which are specific to each taskType.
Currently, there are no additional taskType specific parameters. Once added, they will be described here.
config
Type: dictionary
Type: dictionary
If Translation comes after ASR, and ASR is done in, say Marathi, then Source Language of Translation should be Marathi (ISO Code mr) because the output of ASR (Digital text in Marathi) will be fed to Translation Model.
However, if Translation is the first task or the only task, integrator shall provide appropriate Source Language based on the use case.
Type: dictionary
If TTS comes after Translation, and Translation is done, say from Marathi to Hindi, then Source Language of TTS should be Hindi (ISO Code hi) because the output of Translation (Translated text in Hindi) will be fed to Translation Model.
However, if Translation is the first task or the only task, integrator shall provide appropriate Source Language based on the use case.
Type: Array
This parameter takes an array of tasks, in the form of dictionary of taskType as defined above, that are to be done by the integrator. The sequence of tasks matter. In the above example, the configuration that will be returned back in the response will be for tasks ASR, Translation and TTS in that order.
Each pipelineId (discussed below), may support few individual or task sequences as explained and and detailed out below.
The same has been explained and .
Type: Dictionary
This parameter takes in the configuration requested to do the sequence of tasks defined under parameter .
contains:
language
Type: dictionary
contains:
sourceLanguage
Type: String
Source Language will take the of the language as the input. This parameter will tell the server that integrator wants to receive the information and details about Speech Recognition in this specific language.
contains:
language
Type: dictionary
contains:
sourceLanguage
Type: String
Source Language will take the of the language as the input. This parameter will tell the server that integrator wants to receive the Translation information where the input can be translated FROM this language to another language specified in the targetLanguage below.
and
targetLanguage
Type: String
Target Language will also take the of the language as the input. This parameter will tell the server that integrator wants to receive the Translation information where the input can be translated TOthis language from another language specified un the sourceLanguage above.
contains:
language
Type: dictionary
contains:
sourceLanguage
Type: String
Source Language will take the of the language as the input. This parameter will tell the server that integrator wants to receive the information and details about converting text to speech for this specific language.