Language Models

This documentation provides comprehensive details about the language models available for speech recongition (SR) service.

Endpoint Details

• URL: {{Address}}/v1/speech/dictation/models
• Actor: REST Service Client
• Goal: To see available language models.
• Pre-Conditions: None

Response Example

"Identifier": {
                "Tenant": "Default",
                "Name": "English",
                "Variant": 4,
                "Version": 1

Model Version

Version lets you select the specific model version you want to use for processing your submitted audio.

Use the Latest Version

To utilize the latest version of your chosen model, set ModelVersion=0 or do not send the parameter:

Use an Earlier Version of a Model

To enable the Version feature, include a version parameter when calling Sestek’s API, and set it to the desired model version for processing your submitted audio.

First, call GET models. Learn the version number. Then send your request by giving the version number to ModelVersion parameter.

curl --location '{{Address}}/v1/speech/dictation/request' \
--header 'Content-Type: audio/wave' \
--header 'ModelName: Turkish' \
--header 'ModelVersion: 4' \
--header 'Tenant: Default' \
--header 'Authorization: Bearer Token' \
--data 'audio.wav'

When to Use Versions

• When you want to ensure you are using the latest version of a Sestek model.
• When you need to use an earlier version of a Sestek model.