Skip to content

SpeechApi.md

Latest commit

 

History

History
240 lines (141 loc) · 7.75 KB

SpeechApi.md

File metadata and controls

240 lines (141 loc) · 7.75 KB

SpeechApi

All URIs are relative to /v1

Method HTTP request Description
deleteTranscription DELETE /speech/transcriptions/{transcriptionId} DELETE /speech/transcriptions/{transcriptionId}
getTranscription GET /speech/transcriptions/{transcriptionId} GET /speech/transcriptions/{transcriptionId}
recognize POST /speech/asr POST /speech/asr
recognizeLive GET /speech/asrlive GET /speech/asrlive
recognizeLongRunning POST /speech/asrlongrunning POST /speech/asrlongrunning
speechHealthCheck GET /speech/healthcheck GET /speech/healthcheck

deleteTranscription

DELETE /speech/transcriptions/{transcriptionId}

Deletes a transcription for a previous file using transcriptionId.

Example

farsava-cli deleteTranscription transcriptionId=value

Parameters

Name Type Description Notes
transcriptionId string Id of the transcribed audio. It is a UUID string provided in the speech recognition result. [default to null]

Return type

(empty response body)

Authorization

bearerAuth

HTTP request headers

  • Content-Type: Not Applicable
  • Accept: application/json

[Back to top] [Back to API list] [Back to Model list] [Back to README]

getTranscription

GET /speech/transcriptions/{transcriptionId}

Transcription endpoint enable us to retrieve a previous speech recognition result or inform us on a long running speech recognition status. To access a speech recognition result transcriptionId should be provided.

Example

farsava-cli getTranscription transcriptionId=value

Parameters

Name Type Description Notes
transcriptionId string Id of the transcribed audio. It is a UUID string provided in the speech recognition result. [default to null]

Return type

ASRResponseBody

Authorization

bearerAuth

HTTP request headers

  • Content-Type: Not Applicable
  • Accept: application/json

[Back to top] [Back to API list] [Back to Model list] [Back to README]

recognize

POST /speech/asr

Performs synchronous speech recognition

This resource receives audio data in different formats and transcribes the audio using state-of-the-art deep neural networks. It performs synchronous speech recognition and the result will be availble after all audio has been sent and processed. This endpoint is designed for transcription of short audio files upto 1 minute.

Using config object you can can specify audio configs such as audioEncoding and sampleRateHertz. We will support different languages so you can choose the languageCode. Using asrModel and languageModel in config you can use customized models. Refer to asrLongRunning and WebSocket API for longer audio transcriptions.

Example

farsava-cli recognize

Parameters

Name Type Description Notes
aSRRequestBodyData ASRRequestBodyData ## Audio data along with the customized config is posted to this service for speech recognition.

Return type

ASRResponseBody

Authorization

bearerAuth

HTTP request headers

  • Content-Type: application/json
  • Accept: application/json

[Back to top] [Back to API list] [Back to Model list] [Back to README]

recognizeLive

GET /speech/asrlive

Performs asynchronous live speech recognition using websocket

This resource establish a websocket with client and receives audio data using websocket. It will start transcribing the audio using state-of-the-art deep neural networks and returns the partial results on the websocket. This endpoint is designed for transcription of stream audio data upto 15 minute. It will send back partial (status=partial) result everytime it transcribes an endpoint. After client sends the close signal, it will receive a ASRResponseBody with status=done.

Using config object you can can specify audio configs such as audioEncoding and sampleRateHertz. We will support different languages so you can choose the languageCode. Using asrModel and languageModel in config you can use customized models. Refer to ASRLongRuning API for long audio speech recognition. Refer to ASR API for fast recognition for short audio files.

Example

farsava-cli recognizeLive

Parameters

This endpoint does not need any parameter.

Return type

ASRResponseBody

Authorization

bearerAuth

HTTP request headers

  • Content-Type: Not Applicable
  • Accept: application/json

[Back to top] [Back to API list] [Back to Model list] [Back to README]

recognizeLongRunning

POST /speech/asrlongrunning

Performs asynchronous speech recognition

This resource receives a uri containing the audio resource, download it and transcribes the audio using state-of-the-art deep neural networks. It performs asynchronous speech recognition and the result will be availble using transcription endpoint. This endpoint is designed for transcription of long audio files upto 240 minute.

Using config object you can can specify audio configs such as audioEncoding and sampleRateHertz. We will support different languages so you can choose the languageCode. Using asrModel and languageModel in config you can use customized models. Refer to WebSocket API for speech recognition with streams. Refer to ASR API for fast recognition for short audio files.

Example

farsava-cli recognizeLongRunning

Parameters

Name Type Description Notes
aSRRequestBodyURI ASRRequestBodyURI post uri and configs to this service for asr.

Return type

ASRResponseBody

Authorization

bearerAuth

HTTP request headers

  • Content-Type: application/json
  • Accept: application/json

[Back to top] [Back to API list] [Back to Model list] [Back to README]

speechHealthCheck

GET /speech/healthcheck

speech health check endpoint.

This endpoint will return a simple json including service status and API version.

Example

farsava-cli speechHealthCheck

Parameters

This endpoint does not need any parameter.

Return type

HealthCheckResponseBody

Authorization

bearerAuth

HTTP request headers

  • Content-Type: Not Applicable
  • Accept: application/json

[Back to top] [Back to API list] [Back to Model list] [Back to README]