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

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

Overview

Turn audio into text or text into audio.

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:



147
148
149
 
# File 'lib/openai/resources/audio/transcriptions.rb', line 147

def initialize(client:)
  @client = client
end

Instance Method Details

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

See OpenAI::Resources::Audio::Transcriptions#create_streaming for streaming counterpart.

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

Transcribes audio into the input language.

Returns a transcription object in json, diarized_json, or verbose_json format, or a stream of transcript events.

String, StringIO, and pathless IO inputs are sent with generic upload metadata. Use OpenAI::FilePart when you need to override the filename or content type.

Parameters:

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

    The audio file object (not file name) to transcribe, in one of these formats: fl

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

    ID of the model to use. The options are gpt-transcribe, gpt-4o-transcribe, `

  • chunking_strategy (Symbol, :auto, OpenAI::Models::Audio::TranscriptionCreateParams::ChunkingStrategy::VadConfig, nil) —

    Controls how the audio is cut into chunks. When set to "auto", the server firs

  • include (Array<Symbol, OpenAI::Models::Audio::TranscriptionInclude>) —

    Additional information to include in the transcription response.

  • keywords (Array<String>) —

    Words or phrases to guide transcription of the input audio. Supported by `gpt-tr

  • known_speaker_names (Array<String>) —

    Optional list of speaker names that correspond to the audio samples provided in

  • known_speaker_references (Array<String>) —

    Optional list of audio samples (as [data URLs](https://developer.mozilla.org/en-

  • language (String) —

    The language of the input audio. Supplying the input language in [ISO-639-1](htt

  • languages (Array<String>) —

    Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/w

  • prompt (String) —

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

  • response_format (Symbol, OpenAI::Models::AudioResponseFormat) —

    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

  • timestamp_granularities (Array<Symbol, OpenAI::Models::Audio::TranscriptionCreateParams::TimestampGranularity>) —

    The timestamp granularities to populate for this transcription. `response_format

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

Returns:

See Also:



56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/openai/resources/audio/transcriptions.rb', line 56

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,
    security: {bearer_auth: true},
    options: options
  )
end

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

See OpenAI::Resources::Audio::Transcriptions#create for non-streaming counterpart.

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

Transcribes audio into the input language.

Returns a transcription object in json, diarized_json, or verbose_json format, or a stream of transcript events.

String, StringIO, and pathless IO inputs are sent with generic upload metadata. Use OpenAI::FilePart when you need to override the filename or content type.

Parameters:

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

    The audio file object (not file name) to transcribe, in one of these formats: fl

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

    ID of the model to use. The options are gpt-transcribe, gpt-4o-transcribe, `

  • chunking_strategy (Symbol, :auto, OpenAI::Models::Audio::TranscriptionCreateParams::ChunkingStrategy::VadConfig, nil) —

    Controls how the audio is cut into chunks. When set to "auto", the server firs

  • include (Array<Symbol, OpenAI::Models::Audio::TranscriptionInclude>) —

    Additional information to include in the transcription response.

  • keywords (Array<String>) —

    Words or phrases to guide transcription of the input audio. Supported by `gpt-tr

  • known_speaker_names (Array<String>) —

    Optional list of speaker names that correspond to the audio samples provided in

  • known_speaker_references (Array<String>) —

    Optional list of audio samples (as [data URLs](https://developer.mozilla.org/en-

  • language (String) —

    The language of the input audio. Supplying the input language in [ISO-639-1](htt

  • languages (Array<String>) —

    Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/w

  • prompt (String) —

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

  • response_format (Symbol, OpenAI::Models::AudioResponseFormat) —

    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

  • timestamp_granularities (Array<Symbol, OpenAI::Models::Audio::TranscriptionCreateParams::TimestampGranularity>) —

    The timestamp granularities to populate for this transcription. `response_format

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

Returns:

See Also:



121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
# File 'lib/openai/resources/audio/transcriptions.rb', line 121

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",
      "accept-encoding" => "identity"
    },
    body: parsed,
    stream: OpenAI::Internal::Stream,
    model: OpenAI::Audio::TranscriptionStreamEvent,
    security: {bearer_auth: true},
    options: options
  )
end