pub struct CreateTranscriptionRequest {
pub file: Vec<u8>,
pub include: Option<Vec<TranscriptionInclude>>,
pub language: Option<String>,
pub model: Value,
pub prompt: Option<String>,
pub response_format: Option<AudioResponseFormat>,
pub stream: Option<bool>,
pub temperature: Option<f32>,
pub timestamp_granularities: Option<Vec<String>>,
}Fields§
§file: Vec<u8>The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
include: Option<Vec<TranscriptionInclude>>Additional information to include in the transcription response. logprobs will return the log probabilities of the tokens in the response to understand the model’s confidence in the transcription. logprobs only works with response_format set to json and only with the models gpt-4o-transcribe and gpt-4o-mini-transcribe.
language: Option<String>The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.
model: ValueID of the model to use. The options are gpt-4o-transcribe, gpt-4o-mini-transcribe, and whisper-1 (which is powered by our open source Whisper V2 model).
prompt: Option<String>An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.
response_format: Option<AudioResponseFormat>§stream: Option<bool>If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section of the Speech-to-Text guide for more information. Note: Streaming is not supported for the whisper-1 model and will be ignored.
temperature: Option<f32>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.
timestamp_granularities: Option<Vec<String>>The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are pub supported: word, or segment. pub Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.