Struct CreateSpeechRequest 

pub struct CreateSpeechRequest {
    pub model: String,
    pub input: String,
    pub voice: Voice,
    pub response_format: Option<SpeechResponseFormat>,
    pub speed: Option<f32>,
}

Request for creating speech from text.

Example

use portkey_sdk::model::{CreateSpeechRequest, Voice, SpeechResponseFormat};

let request = CreateSpeechRequest {
    model: "tts-1".to_string(),
    input: "The quick brown fox jumped over the lazy dog.".to_string(),
    voice: Voice::Alloy,
    response_format: Some(SpeechResponseFormat::Mp3),
    speed: Some(1.0),
};

Fields

model: String

TTS model to use (e.g., “tts-1” or “tts-1-hd”)

input: String

The text to generate audio for.

Maximum length is 4096 characters.

voice: Voice

The voice to use for generation.

response_format: Option<SpeechResponseFormat>

The format for the audio output.

speed: Option<f32>

The speed of the generated audio (0.25 to 4.0).

Default is 1.0.

Trait Implementations

impl Clone for CreateSpeechRequest

fn clone(&self) -> CreateSpeechRequest

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CreateSpeechRequest

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CreateSpeechRequest

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CreateSpeechRequest

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.