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
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
post/audio/translations
Translates audio into English.
Domain types
Translation = { text }
TranslationVerbose = { duration, language, text, 1 more... }