Class: Vapi::DeepgramTranscriber

Inherits:

Object

Object
Vapi::DeepgramTranscriber

show all

Defined in:: lib/vapi_server_sdk/types/deepgram_transcriber.rb

Constant Summary collapse

OMIT =

Object.new

Instance Attribute Summary collapse

#additional_properties ⇒ OpenStruct readonly

Additional properties unmapped to the current class definition.
#code_switching_enabled ⇒ Boolean readonly

This automatically switches the transcriber’s language when the customer’s language changes.
#endpointing ⇒ Float readonly

This is the timeout after which Deepgram will send transcription on user silence.
#keywords ⇒ Array<String> readonly

These keywords are passed to the transcription model to help it pick up use-case specific words.
#language ⇒ Vapi::DeepgramTranscriberLanguage readonly

This is the language that will be set for the transcription.
#model ⇒ Vapi::DeepgramTranscriberModel readonly

This is the Deepgram model that will be used.
#smart_format ⇒ Boolean readonly

This will be use smart format option provided by Deepgram.

Class Method Summary collapse

.from_json(json_object:) ⇒ Vapi::DeepgramTranscriber

Deserialize a JSON object to an instance of DeepgramTranscriber.
.validate_raw(obj:) ⇒ Void

Leveraged for Union-type generation, validate_raw attempts to parse the given hash and check each fields type against the current object’s property definitions.

Instance Method Summary collapse

#initialize(model: OMIT, language: OMIT, smart_format: OMIT, code_switching_enabled: OMIT, keywords: OMIT, endpointing: OMIT, additional_properties: nil) ⇒ Vapi::DeepgramTranscriber constructor
#to_json(*_args) ⇒ String

Serialize an instance of DeepgramTranscriber to a JSON object.

Constructor Details

#initialize(model: OMIT, language: OMIT, smart_format: OMIT, code_switching_enabled: OMIT, keywords: OMIT, endpointing: OMIT, additional_properties: nil) ⇒ `Vapi::DeepgramTranscriber`

Parameters:

model (Vapi::DeepgramTranscriberModel) (defaults to: OMIT) —

This is the Deepgram model that will be used. A list of models can be found here: developers.deepgram.com/docs/models-languages-overview
language (Vapi::DeepgramTranscriberLanguage) (defaults to: OMIT) —

This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: developers.deepgram.com/docs/models-languages-overview
smart_format (Boolean) (defaults to: OMIT) —

This will be use smart format option provided by Deepgram. It’s default disabled because it can sometimes format numbers as times but it’s getting better.
code_switching_enabled (Boolean) (defaults to: OMIT) —
This automatically switches the transcriber’s language when the customer’s language changes. Defaults to false. Usage:
- If your customers switch languages mid-call, you can set this to true.
Note:
- To detect language changes, Vapi uses a custom trained model. Languages
supported (X = limited support):
1. Arabic
2. Bengali
3. Cantonese
4. Chinese
5. Chinese Simplified (X)
6. Chinese Traditional (X)
7. English
8. Farsi (X)
9. French
10. German
11. Haitian Creole (X)
12. Hindi
13. Italian
14. Japanese
15. Korean
16. Portuguese
17. Russian
18. Spanish
19. Thai
20. Urdu
21. Vietnamese
- To receive language-change-detected webhook events, add it to
assistant.serverMessages. @default false
keywords (Array<String>) (defaults to: OMIT) —

These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here.
endpointing (Float) (defaults to: OMIT) —
This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: developers.deepgram.com/docs/endpointing. Here are the most important bits:
- Defaults to 10. This is recommended for most use cases to optimize for
latency.
- 10 can cause some missing transcriptions since because of the shorter context.
This mostly happens for one-word utterances. For those uses cases, it’s recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better.
- If neither 10 nor 300 work, contact [email protected] and we’ll find another
solution. @default 10
additional_properties (OpenStruct) (defaults to: nil) —

Additional properties unmapped to the current class definition

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 134

def initialize(model: OMIT, language: OMIT, smart_format: OMIT, code_switching_enabled: OMIT, keywords: OMIT,
               endpointing: OMIT, additional_properties: nil)
  @model = model if model != OMIT
  @language = language if language != OMIT
  @smart_format = smart_format if smart_format != OMIT
  @code_switching_enabled = code_switching_enabled if code_switching_enabled != OMIT
  @keywords = keywords if keywords != OMIT
  @endpointing = endpointing if endpointing != OMIT
  @additional_properties = additional_properties
  @_field_set = {
    "model": model,
    "language": language,
    "smartFormat": smart_format,
    "codeSwitchingEnabled": code_switching_enabled,
    "keywords": keywords,
    "endpointing": endpointing
  }.reject do |_k, v|
    v == OMIT
  end
end

Instance Attribute Details

#additional_properties ⇒ `OpenStruct` (readonly)

Returns Additional properties unmapped to the current class definition.

Returns:

(OpenStruct) —

Additional properties unmapped to the current class definition



71
72
73

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 71

def additional_properties
  @additional_properties
end

#code_switching_enabled ⇒ `Boolean` (readonly)

Returns This automatically switches the transcriber’s language when the customer’s language changes. Defaults to false. Usage:

If your customers switch languages mid-call, you can set this to true.

Note:

To detect language changes, Vapi uses a custom trained model. Languages

supported (X = limited support):

Arabic
Bengali
Cantonese
Chinese
Chinese Simplified (X)
Chinese Traditional (X)
English
Farsi (X)
French
German
Haitian Creole (X)
Hindi
Italian
Japanese
Korean
Portuguese
Russian
Spanish
Thai
Urdu
Vietnamese

To receive language-change-detected webhook events, add it to

assistant.serverMessages. @default false.

Returns:

(Boolean) —
This automatically switches the transcriber’s language when the customer’s language changes. Defaults to false. Usage:
- If your customers switch languages mid-call, you can set this to true.
Note:
- To detect language changes, Vapi uses a custom trained model. Languages
supported (X = limited support):
1. Arabic
2. Bengali
3. Cantonese
4. Chinese
5. Chinese Simplified (X)
6. Chinese Traditional (X)
7. English
8. Farsi (X)
9. French
10. German
11. Haitian Creole (X)
12. Hindi
13. Italian
14. Japanese
15. Korean
16. Portuguese
17. Russian
18. Spanish
19. Thai
20. Urdu
21. Vietnamese
- To receive language-change-detected webhook events, add it to
assistant.serverMessages. @default false



51
52
53

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 51

def code_switching_enabled
  @code_switching_enabled
end

#endpointing ⇒ `Float` (readonly)

Returns This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: developers.deepgram.com/docs/endpointing. Here are the most important bits:

Defaults to 10. This is recommended for most use cases to optimize for

latency.

10 can cause some missing transcriptions since because of the shorter context.

This mostly happens for one-word utterances. For those uses cases, it’s recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better.

If neither 10 nor 300 work, contact [email protected] and we’ll find another

solution. @default 10.

Returns:

(Float) —
This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: developers.deepgram.com/docs/endpointing. Here are the most important bits:
- Defaults to 10. This is recommended for most use cases to optimize for
latency.
- 10 can cause some missing transcriptions since because of the shorter context.
This mostly happens for one-word utterances. For those uses cases, it’s recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better.
- If neither 10 nor 300 work, contact [email protected] and we’ll find another
solution. @default 10



69
70
71

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 69

def endpointing
  @endpointing
end

#keywords ⇒ `Array<String>` (readonly)

Returns These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here.

Returns:

(Array<String>) —

These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here.



55
56
57

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 55

def keywords
  @keywords
end

#language ⇒ `Vapi::DeepgramTranscriberLanguage` (readonly)

Returns This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: developers.deepgram.com/docs/models-languages-overview.

Returns:

(Vapi::DeepgramTranscriberLanguage) —

This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: developers.deepgram.com/docs/models-languages-overview



16
17
18

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 16

def language
  @language
end

#model ⇒ `Vapi::DeepgramTranscriberModel` (readonly)

Returns This is the Deepgram model that will be used. A list of models can be found here: developers.deepgram.com/docs/models-languages-overview.

Returns:

(Vapi::DeepgramTranscriberModel) —

This is the Deepgram model that will be used. A list of models can be found here: developers.deepgram.com/docs/models-languages-overview



12
13
14

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 12

def model
  @model
end

#smart_format ⇒ `Boolean` (readonly)

Returns This will be use smart format option provided by Deepgram. It’s default disabled because it can sometimes format numbers as times but it’s getting better.

Returns:

(Boolean) —

This will be use smart format option provided by Deepgram. It’s default disabled because it can sometimes format numbers as times but it’s getting better.



19
20
21

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 19

def smart_format
  @smart_format
end

Class Method Details

.from_json(json_object:) ⇒ `Vapi::DeepgramTranscriber`

Deserialize a JSON object to an instance of DeepgramTranscriber

Parameters:

json_object (String)

Returns:

(Vapi::DeepgramTranscriber)

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 159

def self.from_json(json_object:)
  struct = JSON.parse(json_object, object_class: OpenStruct)
  parsed_json = JSON.parse(json_object)
  model = parsed_json["model"]
  language = parsed_json["language"]
  smart_format = parsed_json["smartFormat"]
  code_switching_enabled = parsed_json["codeSwitchingEnabled"]
  keywords = parsed_json["keywords"]
  endpointing = parsed_json["endpointing"]
  new(
    model: model,
    language: language,
    smart_format: smart_format,
    code_switching_enabled: code_switching_enabled,
    keywords: keywords,
    endpointing: endpointing,
    additional_properties: struct
  )
end

.validate_raw(obj:) ⇒ `Void`

Leveraged for Union-type generation, validate_raw attempts to parse the given

hash and check each fields type against the current object's property
definitions.

Parameters:

obj (Object)

Returns:

(Void)

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 192

def self.validate_raw(obj:)
  obj.model&.is_a?(Vapi::DeepgramTranscriberModel) != false || raise("Passed value for field obj.model is not the expected type, validation failed.")
  obj.language&.is_a?(Vapi::DeepgramTranscriberLanguage) != false || raise("Passed value for field obj.language is not the expected type, validation failed.")
  obj.smart_format&.is_a?(Boolean) != false || raise("Passed value for field obj.smart_format is not the expected type, validation failed.")
  obj.code_switching_enabled&.is_a?(Boolean) != false || raise("Passed value for field obj.code_switching_enabled is not the expected type, validation failed.")
  obj.keywords&.is_a?(Array) != false || raise("Passed value for field obj.keywords is not the expected type, validation failed.")
  obj.endpointing&.is_a?(Float) != false || raise("Passed value for field obj.endpointing is not the expected type, validation failed.")
end

Instance Method Details

#to_json(*_args) ⇒ `String`

Serialize an instance of DeepgramTranscriber to a JSON object

Returns:

(String)



182
183
184

# File 'lib/vapi_server_sdk/types/deepgram_transcriber.rb', line 182

def to_json(*_args)
  @_field_set&.to_json
end

Class: Vapi::DeepgramTranscriber

Constant Summary collapse

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(model: OMIT, language: OMIT, smart_format: OMIT, code_switching_enabled: OMIT, keywords: OMIT, endpointing: OMIT, additional_properties: nil) ⇒ Vapi::DeepgramTranscriber

Instance Attribute Details

#additional_properties ⇒ OpenStruct (readonly)

#code_switching_enabled ⇒ Boolean (readonly)

#endpointing ⇒ Float (readonly)

#keywords ⇒ Array<String> (readonly)

#language ⇒ Vapi::DeepgramTranscriberLanguage (readonly)

#model ⇒ Vapi::DeepgramTranscriberModel (readonly)

#smart_format ⇒ Boolean (readonly)

Class Method Details

.from_json(json_object:) ⇒ Vapi::DeepgramTranscriber

.validate_raw(obj:) ⇒ Void

Instance Method Details

#to_json(*_args) ⇒ String

#initialize(model: OMIT, language: OMIT, smart_format: OMIT, code_switching_enabled: OMIT, keywords: OMIT, endpointing: OMIT, additional_properties: nil) ⇒ `Vapi::DeepgramTranscriber`

#additional_properties ⇒ `OpenStruct` (readonly)

#code_switching_enabled ⇒ `Boolean` (readonly)

#endpointing ⇒ `Float` (readonly)

#keywords ⇒ `Array<String>` (readonly)

#language ⇒ `Vapi::DeepgramTranscriberLanguage` (readonly)

#model ⇒ `Vapi::DeepgramTranscriberModel` (readonly)

#smart_format ⇒ `Boolean` (readonly)

.from_json(json_object:) ⇒ `Vapi::DeepgramTranscriber`

.validate_raw(obj:) ⇒ `Void`

#to_json(*_args) ⇒ `String`