Struct SpeechRequest 

pub struct SpeechRequest {
    pub input: String,
    pub model: String,
    pub voice: SpeechVoice,
    pub instructions: Option<String>,
    pub response_format: Option<SpeechFormat>,
    pub speed: Option<f32>,
    pub stream_format: Option<SpeechStreamFormat>,
}

Generates audio from the input text.

Fields

input: String

The text to generate audio for. The maximum length is 4096 characters.

model: String

One of the available TTS models: tts-1, tts-1-hd, gpt-4o-mini-tts, or gpt-4o-mini-tts-2025-12-15.

voice: SpeechVoice

The voice to use when generating the audio.

Supported built-in voices are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, verse, marin, and cedar. A custom voice object with an id may also be provided, for example { "id": "voice_1234" }.

instructions: Option<String>

Control the voice of your generated audio with additional instructions. Does not work with tts-1 or tts-1-hd.

response_format: Option<SpeechFormat>

The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm.

speed: Option<f32>

The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.

stream_format: Option<SpeechStreamFormat>

The format to stream the audio in. Supported formats are sse and audio. sse is not supported for tts-1 or tts-1-hd.

When set, send the request through PostBinary::get_stream_response_bytes to receive the response as a stream of byte chunks instead of a single buffered body.

Trait Implementations

impl Clone for SpeechRequest

fn clone(&self) -> SpeechRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SpeechRequest

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

Formats the value using the given formatter.

impl Default for SpeechRequest

fn default() -> SpeechRequest

Returns the “default value” for a type.

impl Post for SpeechRequest

fn build_url(&self, base_url: &str) -> Result<String, OapiError>

Builds the URL for the request.

base_url should be like https://api.openai.com/v1

fn is_streaming(&self) -> bool

impl PostBinary for SpeechRequest

fn get_response_bytes( &self, client: &Client, base_url: &str, api_key: &str, ) -> impl Future<Output = Result<Vec<u8>, OapiError>> + Send + Sync

Sends a POST request with a JSON body and returns the raw response body bytes.

fn get_stream_response_bytes( &self, client: &Client, base_url: &str, api_key: &str, ) -> impl Future<Output = Result<impl Stream<Item = Result<Vec<u8>, OapiError>> + Send + Unpin + 'static, OapiError>> + Send + Sync

Sends a POST request with a JSON body and streams the raw response body as byte chunks.

impl Serialize for SpeechRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.