TranscriptionRequest class
Properties
-
bufferedBytes
→ BufferedBytes?
-
Bytes array from data buffer with format, which is one of these: mp3, mp4, mpeg,
mpga, m4a, wav, or webm.
no setterinherited
-
copyWith
→ $TranscriptionRequestCopyWith<TranscriptionRequest>
-
no setterinherited
-
file
→ String?
-
The audio file to transcribe, in one of these formats: mp3, mp4, mpeg,
mpga, m4a, wav, or webm.
no setterinherited
-
hashCode
→ int
-
The hash code for this object.
no setterinherited
-
language
→ String?
-
The language of the input audio. Supplying the input language in
ISO-639-1
format will improve accuracy and latency.
no setterinherited
-
model
→ String
-
ID of the model to use. Only Models.whisper_1 is currently available.
no setterinherited
-
prompt
→ String?
-
An optional text to guide the model's style or continue a previous audio
segment. The prompt should match the audio language.
no setterinherited
-
responseFormat
→ String?
-
The format of the transcript output, in one of these options: json,
text, srt, verbose_json, or vtt. Defaults to json.
no setterinherited
-
runtimeType
→ Type
-
A representation of the runtime type of the object.
no setterinherited
-
temperature
→ double?
-
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. Defaults to 0.
no setterinherited