sttp.openai.requests.audio.transcriptions

Members list

Type members

Classlikes

sealed abstract class Language(val value: String)

Attributes

Companion
object
Supertypes
class Object
trait Matchable
class Any
Known subtypes
object Armenian
object Azerbaijani
object Belarusian
object Bosnian
object Bulgarian
object Catalan
object Chinese
object Croatian
class Custom
object Czech
object Danish
object Dutch
object English
object Estonian
object Finnish
object French
object Galician
object German
object Greek
object Hebrew
object Hindi
object Hungarian
object Icelandic
object Indonesian
object Italian
object Japanese
object Kannada
object Kazakh
object Korean
object Latvian
object Lithuanian
object Macedonian
object Malay
object Maori
object Marathi
object Nepali
object Norwegian
object Persian
object Polish
object Portuguese
object Romanian
object Russian
object Serbian
object Slovak
object Slovenian
object Spanish
object Swahili
object Swedish
object Tagalog
object Tamil
object Thai
object Turkish
object Ukrainian
object Urdu
object Vietnamese
object Welsh
Show all
object Language

Attributes

Companion
class
Supertypes
trait Sum
trait Mirror
class Object
trait Matchable
class Any
Self type
Language.type
case class TranscriptionConfig(file: File, model: RecognitionModel, prompt: Option[String], responseFormat: Option[ResponseFormat], temperature: Option[Float], language: Option[Language])

Value parameters

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.

Attributes

Companion
object
Supertypes
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all

Attributes

Companion
class
Supertypes
trait Product
trait Mirror
class Object
trait Matchable
class Any
Self type