language
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 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 language: String?
import OpenAI
struct AudioTranscriptionQuery
@frozen struct String
A Unicode string value that is a collection of characters.
init(file: Data, fileType: Self.FileType, model: Model, prompt: String? = nil, temperature: Double? = nil, language: String? = nil, responseFormat: Self.ResponseFormat? = nil)
init(from decoder: any Decoder) throws
let file: Data
The 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.FileType
let model: Model
ID 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
enum FileType
enum ResponseFormat