ark::openai::TranscribeRequest

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

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

core::ByteBuffer audio
std::string model= “whisper-1”
The name of the model to use. Defaults to whisper-1.
std::optional< std::string > prompt
An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.
std::optional< std::string > language
The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.