OpenAI API

Audio

audio

Domain types

AudioModel = "whisper-1"
AudioResponseFormat = "json" | "text" | "srt" | 2 more...
Audio

Speech

audio.speech

Methods

Create Speech -> unknown
post/audio/speech

Generates audio from the input text.

Domain types

SpeechModel = "tts-1" | "tts-1-hd"
Audio

Transcriptions

audio.transcriptions

Methods

Create Transcription ->
Transcription
|
TranscriptionVerbose
post/audio/transcriptions

Transcribes audio into the input language.

Domain types

Transcription = { text }
TranscriptionSegment = { id, avg_logprob, compression_ratio, 7 more... }
TranscriptionVerbose = { duration, language, text, 2 more... }
TranscriptionWord = { end, start, word }
Audio

Translations

audio.translations

Methods

Create Translation ->
Translation
|
TranslationVerbose
post/audio/translations

Translates audio into English.

Security
Bearer Auth

Example: Authorization: Bearer My API Key

Body parameters
file: string

The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

model: string |
AudioModel

ID of the model to use. Only whisper-1 (which is powered by our open source Whisper V2 model) is currently available.

prompt?: string

An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English.

response_format?:
AudioResponseFormat

The format of the output, in one of these options: json, text, srt, verbose_json, or vtt.

temperature?: number

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.

Response fields
Translation = { text }
TranslationVerbose = { duration, language, text, 1 more... }
Request example
200Example

Domain types

Translation = { text }
TranslationVerbose = { duration, language, text, 1 more... }