AudioTranslationQuery
Translates audio into English.
struct AudioTranslationQuery
Translates audio into English.
struct AudioTranslationQuery
import OpenAI
protocol Copyable
A type whose values can be implicitly or explicitly copied.
protocol Decodable
A type that can decode itself from an external representation.
protocol Encodable
A type that can encode itself to an external representation.
protocol Escapable
init(file: Data, fileType: Self.FileType, model: Model, prompt: String? = nil, temperature: Double? = nil, responseFormat: Self.ResponseFormat? = nil)
init(from decoder: any Decoder) throws
let file: Data
The audio file object (not file name) translate, 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 be in English. https://platform.openai.com/docs/guides/speech-to-text/prompting
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
typealias FileType = AudioTranscriptionQuery.FileType
typealias ResponseFormat = AudioTranscriptionQuery.ResponseFormat