# POST /speech/languagemodels

**POST /speech/languagemodels**

Train a custom language model using pharases provided by user. Returning a languageModelId for accessing the language model later and using this custom language model to transcribe audios. Using custom language models will boost accuracy for specific keywords/phrases and can be used for a domain-specific speech recognition.
***



## Servers


## Authentication methods
- Bearer auth


## Parameters



### Body:  (object)
A json object including a name and a corpora. Corpora is a array of text data to train a custom model. This text data can be keywords/phrases. All values in the array must be a string. Name is an arbitary string you set for the custom language model name.
- **corpora** (array[string])
  An array of text data to train a custom model. This text data can be keywords/phrases, or historical transcripts (transcriptionId of previous speechRecognitionResult). All values in the array must be a string.
      
- **name** (string)
  The name of the custom language model being created.


## Responses
### 201
OK. Processing and Training Language Model.

#### Body:  (object)
- **languageModelId** (string)
  This is the language model id of a customized trained language model. You can train your own language models and then use them to recognize speech. Refer to [languagemodel/train](#languagemodel/train) for more info.

    There are some pretrained language models which you can use.

    Model | Description
    ------------ | -------------
    general | Best for audio content that is not one of the specific language models. This is the default language model and if you are not sure which one to use, simply use 'general'.
    numbers | Best for audio content that contains only spoken numbers. For examble this language model can be used for speech enabled number input fileds.
    yesno | Best for audio content that contains yes or no. For examble this language model can be used to receive confirmation from user.
    country | Best for audio content that contains only spoken country. For examble this language model can be used for speech enabled input fileds.
    city | Best for audio content that contains only spoken city. For examble this language model 
      can be used for speech enabled input fileds.
    career | Best for audio content that contains only spoken career names. For examble this language model can be used for speech enabled input fileds.
- **name** (string)
  The name of the custom language model.
- **status** (string)
  Status of the language model training process. After a language model training finishes it can be used for speech recognition using its languageModelId.

### 501
The request method is not supported by the server and cannot be handled.


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.

### 400
This response means that server could not understand the request due to invalid syntax.


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.

### 401
Authentication is needed to get requested response. This is similar to 403, but in this case, authentication is possible.


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.

### 403
Client does not have access rights to the content so server is rejecting to give proper response.


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.

### 405
The request method is known by the server but has been disabled and cannot be used.


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.

### 429
The user has sent too many requests in a given amount of time ("rate limiting").


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.

### 500
The server has encountered a situation it doesn't know how to handle.


#### Body:  (object)
- **status** (string)
  HTTP response status code.
- **detail** (string)
  Message explaining the issue.
- **title** (string)
  Error message title.
- **type** (string)
  Error type.


[Powered by Bump.sh](https://bump.sh)