class

AI::OpenAI::OpenAISpeechModel

Inherits AI::Provider::SpeechModel::V3 < Reference < Object

OpenAI speech model implementation.

Implements the SpeechModelV3 interface for text-to-speech synthesis using OpenAI's audio/speech API.

Supports models:

  • tts-1 - Fast text-to-speech model
  • tts-1-hd - High-definition text-to-speech model
  • gpt-4o-mini-tts - GPT-4o mini text-to-speech model

Example:

model = OpenAISpeechModel.new("tts-1", config)
result = model.do_generate(
  Provider::SpeechModel::CallOptions.new(
    text: "Hello, world!",
    voice: "alloy"
  )
)
File.write("output.mp3", result.audio)

Constructors

new(model_id : OpenAISpeechModelId, config : OpenAIConfig)
Source
new(model_id : OpenAISpeechModelId, config : OpenAISpeechModelConfig)
Source

Instance methods

do_generate(options : Provider::SpeechModel::CallOptions) : Provider::SpeechModel::Result

Generates speech audio from text.

Parameters:

  • options: Call options including text, voice, format, and speed

Returns speech result with audio data and metadata.

Source
model_id

The model ID.

Source
provider

Returns the provider name.

Source
specification_version

Returns the specification version.

Source