Class: OpenAI::Resources::Audio::Speech

Inherits:

Object

• Object
• OpenAI::Resources::Audio::Speech

Defined in:

lib/openai/resources/audio/speech.rb

Overview

Turn audio into text or text into audio.

Instance Method Summary

• #create(input:, model:, voice:, instructions: nil, response_format: nil, speed: nil, stream_format: nil, request_options: {}) ⇒ StringIO

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

• #initialize(client:) ⇒ Speech constructor private

  A new instance of Speech.

Constructor Details

#initialize(client:) ⇒ Speech

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 Speech.

Parameters:

• client (OpenAI::Client)

# File 'lib/openai/resources/audio/speech.rb', line 51

def initialize(client:)
  @client = client
end

Instance Method Details

#create(input:, model:, voice:, instructions: nil, response_format: nil, speed: nil, stream_format: nil, request_options: {}) ⇒ StringIO

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

Generates audio from the input text.

Returns the audio file content, or a stream of audio events.

Parameters:

• input (String) —

  The text to generate audio for. The maximum length is 4096 characters.

• model (String, Symbol, OpenAI::Models::Audio::SpeechModel) —

  One of the available [TTS models](platform.openai.com/docs/models#tts):

• voice (String, Symbol, OpenAI::Models::Audio::SpeechCreateParams::Voice::ID, OpenAI::Models::Audio::SpeechCreateParams::Voice) —

  The voice to use when generating the audio. Supported built-in voices are ‘alloy

• instructions (String) —

  Control the voice of your generated audio with additional instructions. Does not

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

  The format to audio in. Supported formats are ‘mp3`, `opus`, `aac`, `flac`, `wav

• speed (Float) —

  The speed of the generated audio. Select a value from ‘0.25` to `4.0`. `1.0` is

• stream_format (Symbol, OpenAI::Models::Audio::SpeechCreateParams::StreamFormat) —

  The format to stream the audio in. Supported formats are ‘sse` and `audio`. `sse

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

Returns:

• (StringIO)

See Also:

• Models::Audio::SpeechCreateParams

# File 'lib/openai/resources/audio/speech.rb', line 36

def create(params)
  parsed, options = OpenAI::Audio::SpeechCreateParams.dump_request(params)
  @client.request(
    method: :post,
    path: "audio/speech",
    headers: {"accept" => "application/octet-stream"},
    body: parsed,
    model: StringIO,
    options: options
  )
end