audio_transcription_request {oaii}

API audio: speech to text (transcryption)

Description

Transcribes audio into the input language. To get more details, visit https://platform.openai.com/docs/api-reference/audio/createTranscription https://platform.openai.com/docs/guides/speech-to-text

Usage

audio_transcription_request(
  file,
  model,
  language = NULL,
  prompt = NULL,
  response_format = NULL,
  temperature = NULL,
  file_type = NULL,
  api_key = api_get_key()
)

Arguments

file

string/raw, content of the audio file or path to the audio file to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

model

string, ID of the model to use. Only 'whisper-1' is currently available.

language

NULL/string, the language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. See https://en.wikipedia.org/wiki/List_of_ISO_639_language_codes

prompt

NULL/string, an optional text to guide the model's style or continue a previous audio segment. The prompt (https://platform.openai.com/docs/guides/speech-to-text/prompting) should match the audio language.

response_format

NULL/string, The format of the transcript output, in one of these options: json (default), text, srt, verbose_json, or vtt.

temperature

NULL/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. 0 is default.

file_type

NULL/string mime type of file (e.g. "audio/mpeg"). If NULL (default), will be guess by mime::guess_type() when needed.

api_key

string, OpenAI API key (see https://platform.openai.com/account/api-keys)

Value

content of the httr response object or SimpleError (conditions) enhanced with two additional fields: 'status_code' (response$status_code) and 'message_long' (built on response content)

Examples

## Not run: 
res_content <- audio_speech_request(
  "path/to/audio/file.mp3",
  "whisper-1",
  "en",
  response_format = "text"
)
if (!is_error(res_content)) {
  message(res_content)
}

## End(Not run)