Method: OpenAI::Resources::Audio::Translations#create

Defined in:
lib/openai/resources/audio/translations.rb

#create(file: , model: , prompt: nil, response_format: nil, temperature: nil, request_options: {}) ⇒ OpenAI::Models::Audio::Translation, OpenAI::Models::Audio::TranslationVerbose

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

Translates audio into English.

Parameters:

  • file (Pathname, StringIO, IO, String, OpenAI::FilePart) —

    The audio file object (not file name) translate, in one of these formats: flac,

  • model (String, Symbol, OpenAI::Models::AudioModel) —

    ID of the model to use. Only whisper-1 (which is powered by our open source Wh

  • prompt (String) —

    An optional text to guide the model's style or continue a previous audio segment

  • response_format (Symbol, OpenAI::Models::Audio::TranslationCreateParams::ResponseFormat) —

    The format of the output, in one of these options: json, text, srt, `verbo

  • temperature (Float) —

    The sampling temperature, between 0 and 1. Higher values like 0.8 will make the

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/openai/resources/audio/translations.rb', line 29

def create(params)
  parsed, options = OpenAI::Audio::TranslationCreateParams.dump_request(params)
  @client.request(
    method: :post,
    path: "audio/translations",
    headers: {"content-type" => "multipart/form-data"},
    body: parsed,
    model: OpenAI::Models::Audio::TranslationCreateResponse,
    options: options
  )
end