pub struct CreateTranscriptionRequestArgs { /* private fields */ }
Expand description
Builder for CreateTranscriptionRequest
.
Implementations§
Source§impl CreateTranscriptionRequestArgs
impl CreateTranscriptionRequestArgs
Sourcepub fn file<VALUE: Into<AudioInput>>(&mut self, value: VALUE) -> &mut Self
pub fn file<VALUE: Into<AudioInput>>(&mut self, value: VALUE) -> &mut Self
The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
Sourcepub fn model<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
pub fn model<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
ID of the model to use. Only whisper-1
(which is powered by our open source Whisper V2 model) is currently available.
Sourcepub fn prompt<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
pub fn prompt<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.
Sourcepub fn response_format<VALUE: Into<AudioResponseFormat>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn response_format<VALUE: Into<AudioResponseFormat>>( &mut self, value: VALUE, ) -> &mut Self
The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
Sourcepub fn temperature<VALUE: Into<f32>>(&mut self, value: VALUE) -> &mut Self
pub fn temperature<VALUE: Into<f32>>(&mut self, value: VALUE) -> &mut Self
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.
Sourcepub fn language<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
pub fn language<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
Sourcepub fn timestamp_granularities<VALUE: Into<Vec<TimestampGranularity>>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn timestamp_granularities<VALUE: Into<Vec<TimestampGranularity>>>( &mut self, value: VALUE, ) -> &mut Self
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 supported: word
, or segment
. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.
Sourcepub fn build(&self) -> Result<CreateTranscriptionRequest, OpenAIError>
pub fn build(&self) -> Result<CreateTranscriptionRequest, OpenAIError>
Trait Implementations§
Source§impl Clone for CreateTranscriptionRequestArgs
impl Clone for CreateTranscriptionRequestArgs
Source§fn clone(&self) -> CreateTranscriptionRequestArgs
fn clone(&self) -> CreateTranscriptionRequestArgs
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source
. Read more