Class: OpenAI::Resources::Audio::Transcriptions

Inherits:
Object
  • Object
show all
Defined in:
lib/openai/resources/audio/transcriptions.rb

Instance Method Summary collapse

Constructor Details

#initialize(client:) ⇒ Transcriptions

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of Transcriptions.

Parameters:



110
111
112
 
# File 'lib/openai/resources/audio/transcriptions.rb', line 110

def initialize(client:)
  @client = client
end

Instance Method Details

#create(file: , model: , chunking_strategy: nil, include: nil, language: nil, prompt: nil, response_format: nil, temperature: nil, timestamp_granularities: nil, request_options: {}) ⇒ OpenAI::Models::Audio::Transcription, OpenAI::Models::Audio::TranscriptionVerbose

See #create_streaming for streaming counterpart.

Some parameter documentations has been truncated, see Models::Audio::TranscriptionCreateParams for more details.

Transcribes audio into the input language.

Parameters:

Returns:

See Also:



40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
 
# File 'lib/openai/resources/audio/transcriptions.rb', line 40

def create(params)
  parsed, options = OpenAI::Audio::TranscriptionCreateParams.dump_request(params)
  if parsed[:stream]
    message = "Please use `#create_streaming` for the streaming use case."
    raise ArgumentError.new(message)
  end
  @client.request(
    method: :post,
    path: "audio/transcriptions",
    headers: {"content-type" => "multipart/form-data"},
    body: parsed,
    model: OpenAI::Models::Audio::TranscriptionCreateResponse,
    options: options
  )
end

#create_streaming(file: , model: , chunking_strategy: nil, include: nil, language: nil, prompt: nil, response_format: nil, temperature: nil, timestamp_granularities: nil, request_options: {}) ⇒ OpenAI::Internal::Stream<OpenAI::Models::Audio::TranscriptionTextDeltaEvent, OpenAI::Models::Audio::TranscriptionTextDoneEvent>

See #create for non-streaming counterpart.

Some parameter documentations has been truncated, see Models::Audio::TranscriptionCreateParams for more details.

Transcribes audio into the input language.

Parameters:

Returns:

See Also:



89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
# File 'lib/openai/resources/audio/transcriptions.rb', line 89

def create_streaming(params)
  parsed, options = OpenAI::Audio::TranscriptionCreateParams.dump_request(params)
  unless parsed.fetch(:stream, true)
    message = "Please use `#create` for the non-streaming use case."
    raise ArgumentError.new(message)
  end
  parsed.store(:stream, true)
  @client.request(
    method: :post,
    path: "audio/transcriptions",
    headers: {"content-type" => "multipart/form-data", "accept" => "text/event-stream"},
    body: parsed,
    stream: OpenAI::Internal::Stream,
    model: OpenAI::Audio::TranscriptionStreamEvent,
    options: options
  )
end