init(model: Model, input: String, voice: AudioSpeechVoice, instructions: String = "", responseFormat: AudioSpeechResponseFormat = .mp3, speed: Double = 1.0) s6OpenAI16AudioSpeechQueryV5model5input5voice12instructions14responseFormat5speedACSS_SSAC0cD5VoiceOSSAC0cd8ResponseK0OSdtcfc What are these?90YKUimport OpenAIstruct AudioSpeechQueryGenerates audio from the input text. Learn more: OpenAI Speech – Documentation
typealias Model = StringDefines all available OpenAI models supported by the library.
@frozen struct StringA Unicode string value that is a collection of characters.
enum AudioSpeechVoiceEncapsulates the voices available for audio generation.
enum AudioSpeechResponseFormatEncapsulates the response formats available for audio data.
@frozen struct DoubleA double-precision, floating-point value type.
init(from decoder: any Decoder) throws static func normalizeSpeechSpeed(_ inputSpeed: Double?) -> Double let input: StringThe text to generate audio for. The maximum length is 4096 characters.
let instructions: String?Control the voice of your generated audio with additional instructions. Does not work with tts-1 or tts-1-hd.
let model: ModelOne of the available TTS models: tts-1 or tts-1-hd
let responseFormat: AudioSpeechResponseFormat?The format to audio in. Supported formats are mp3, opus, aac, flac, and pcm. Defaults to mp3
let speed: Double?The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default. Defaults to 1
let voice: AudioSpeechVoiceThe voice to use when generating the audio. Supported voices are alloy, echo, fable, onyx, nova, and shimmer. Previews of the voices are available in the Text to speech guide. https://platform.openai.com/docs/guides/text-to-speech/voice-options
enum CodingKeysenum Speed