ark::openai::TextToSpeechRequest

Defined in header “ark/openai/openai_tts.hh”.

Represents a request for a text-to-speech (to convert some input message into audio).

std::string model_name= “tts-1”
The name of the model to use. Defaults to tts-1.
std::string voice= “alloy”
The voice to use (as of this writing, it can be alloy, echo, fable, onyx, nova, or shimmer.
std::string response_format= “mp3”
The response format (format of the generated audio, which as of this writing can be one of mp3, opus, aac, flac, wav, or pcm).
double speed= 1.0
Voice speed multiplier.
std::string message
The input message to translate into speec.