Speech Recognition Component (Yandex Cloud SpeechKit)
Description
Performs caller speech recognition into text form.
The service is provided by Yandex Cloud SpeechKit over the protocol HTTP. It has no technical limitations in terms of performance.
For the procedure of registering a Yandex-cloud account and the cost of the service, see Yandex.
The tokens are configured in domain settings, field 'yandex_cloud'..
Allows you to interrupt on silence after a spoken phrase.
Index |
|
Short title |
|
Types of scenarios |
|
Starter module |
|
Mode |
Asynchronous |
Icon |
![]() |
Branching pattern |
Branching, interrupting |
Properties
Specification | Description |
---|---|
Title: |
Specifies the Yandex account whose options are taken to connect to yandex. |
Title: |
Yandex Cloud SpeechKit recognition service parameter: recognition theme.
|
Title: |
Argument containing a custom theme for the recognition service Yandex Cloud SpeechKit. |
Title: |
Yandex Cloud SpeechKit recognition service parameter: recognition language.
|
Title: |
Yandex Cloud SpeechKit recognition service parameter: switch off the profanity filter. |
Title: |
Maximum allowable recording time from the end of preplay, in seconds. |
Title: |
DTMF detector switch. Opens the settings for the character save and operation interrupt modes. |
Title: |
Variable to store received DTMF characters. |
Title: |
Buffer pre-clearance switch DTMF. |
Title: |
An argument containing a limit on the number of characters that can be entered. |
Title: |
A string containing sequences of interrupt characters separated by commas. |
Title: |
Voice Detector (VAD) switch to automatically end recording and send the last portion of voice data to the recognition service. |
Title: |
Interval for the Voice Action Detector (VAD) to automatically stop recording and send the last portion of voice data to the recognition service. |
Title: |
An argument containing the VAD threshold at which the presence of voice is detected when crossed upwards, in decibels. |
Title: |
Timeout for waiting for a response from the Yandex Cloud SpeechKit recognition service after sending it the last portion of voice data. |
Title: |
Variable to save the text result of recognition. |
Title: |
Variable to store the HTTP response code of the recognition service. |
Title: |
Variable to store the full content of the HTTP response of the recognition service. |
Title: |
Switch to save the record file sent to the recognition service. |
Title: |
Variable to store the path to the record file. The recording is made on the server with the mg role serving the current call, and then transferred to the server with the ivr role serving the current scenario. The transfer always takes place within the site. |
Title: |
Pre-play audio file to the subscriber during which the voice detector is also activated. Can be selected in one of the modes:
|
Title: |
Component to which control is passed in case of successful completion of the operation. |
Title: |
The component to which control is passed in case the timeout period for HTTP response from the recognition service has expired. |
Title: |
The component to which control is passed if an error occurs. |