sttp.openai.requests.audio.transcriptions
Members list
Concise view
Type members
Classlikes
Attributes
- Companion:
- object
- Graph
- Supertypes
- class Objecttrait Matchableclass Any
- Known subtypes
- object Armenian.typeobject Azerbaijani.typeobject Belarusian.typeobject Bosnian.typeobject Bulgarian.typeobject Catalan.typeobject Chinese.typeobject Croatian.typeclass Customobject Czech.typeobject Danish.typeobject Dutch.typeobject English.typeobject Estonian.typeobject Finnish.typeobject French.typeobject Galician.typeobject German.typeobject Greek.typeobject Hebrew.typeobject Hindi.typeobject Hungarian.typeobject Icelandic.typeobject Indonesian.typeobject Italian.typeobject Japanese.typeobject Kannada.typeobject Kazakh.typeobject Korean.typeobject Latvian.typeobject Lithuanian.typeobject Macedonian.typeobject Malay.typeobject Maori.typeobject Marathi.typeobject Nepali.typeobject Norwegian.typeobject Persian.typeobject Polish.typeobject Portuguese.typeobject Romanian.typeobject Russian.typeobject Serbian.typeobject Slovak.typeobject Slovenian.typeobject Spanish.typeobject Swahili.typeobject Swedish.typeobject Tagalog.typeobject Tamil.typeobject Thai.typeobject Turkish.typeobject Ukrainian.typeobject Urdu.typeobject Vietnamese.typeobject Welsh.type
object Language
case class TranscriptionConfig(file: File, model: RecognitionModel, prompt: Option[String], responseFormat: Option[ResponseFormat], temperature: Option[Float], language: Option[Language])
Attributes
- file
The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
- language
The language of the input audio, use one of
Language
- model
ID of the model to use. Only whisper-1 is currently available.
- prompt
An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
- responseFormat
The format of the transcript output, one of
ResponseFormat
- temperature
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.
- Companion:
- object
- Graph
- Supertypes
- trait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass Any
object TranscriptionConfig
Attributes
- Companion:
- class
- Graph
- Supertypes
- trait Producttrait Mirrorclass Objecttrait Matchableclass Any
- Self type
- TranscriptionConfig.type