Struct TranscriptionRequest 

pub struct TranscriptionRequest {
    pub audio: AudioInput,
    pub model: String,
    pub language: Option<String>,
    pub prompt: Option<String>,
    pub response_format: Option<TranscriptFormat>,
    pub timestamp_granularities: Option<Vec<TimestampGranularity>>,
}

Request for transcribing audio to text.

Fields

audio: AudioInput

The audio to transcribe.

model: String

The model to use (e.g., “whisper-1”).

language: Option<String>

Language of the audio (ISO-639-1 code).

prompt: Option<String>

Prompt to guide transcription style.

response_format: Option<TranscriptFormat>

Response format.

timestamp_granularities: Option<Vec<TimestampGranularity>>

Timestamp granularities to include.

Implementations

impl TranscriptionRequest

pub fn new(model: impl Into<String>, audio: AudioInput) -> Self

Create a new transcription request.

pub fn with_language(self, language: impl Into<String>) -> Self

Set the language.

pub fn with_prompt(self, prompt: impl Into<String>) -> Self

Set a prompt to guide transcription.

pub fn with_format(self, format: TranscriptFormat) -> Self

Set the response format.

pub fn with_word_timestamps(self) -> Self

Enable word-level timestamps.

pub fn with_segment_timestamps(self) -> Self

Enable segment-level timestamps.

Trait Implementations

impl Clone for TranscriptionRequest

fn clone(&self) -> TranscriptionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TranscriptionRequest

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

Formats the value using the given formatter.