init(file: Data, fileType: Self.FileType, model: Model, prompt: String? = nil, temperature: Double? = nil, language: String? = nil, responseFormat: Self.ResponseFormat? = nil, timestampGranularities: [Self.TimestampGranularities] = []) s6OpenAI23AudioTranscriptionQueryV4file0F4Type5model6prompt11temperature8language14responseFormat22timestampGranularitiesAC20FoundationEssentials4DataV_AC04FileG0OS2SSgSdSgAqC08ResponseM0OSgSayAC09TimestampO0OGtcfc What are these?63EK5import OpenAIstruct AudioTranscriptionQuery@frozen struct Dataenum FileTypetypealias Model = StringDefines all available OpenAI models supported by the library.
@frozen struct StringA Unicode string value that is a collection of characters.
@frozen struct DoubleA double-precision, floating-point value type.
enum ResponseFormatenum TimestampGranularitiesinit(from decoder: any Decoder) throws let file: DataThe audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
let fileType: Self.FileTypelet language: String?The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. https://platform.openai.com/docs/guides/speech-to-text/prompting
let model: ModelID of the model to use. Only whisper-1 is currently available.
let prompt: String?An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.
let responseFormat: Self.ResponseFormat?The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt. Defaults to json
let temperature: Double?The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit. Defaults to 0
let timestampGranularities: [Self.TimestampGranularities]The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. Defaults to segment