Speech To Text

Speech to Text

from aibrary import AiBrary

aibrary = AiBrary()
aibrary.audio.transcriptions.create(
    model="whisper-1", file=open("path/to/audio", "rb")
)

Generation

post

Authorizations

Body

modelstringrequired

ID of the model to use

languageany ofoptional

Language in ISO-639-1 format

promptany ofoptional

Optional text to guide the model's style or continue a previous audio segment

Default: ""

response_formatstring · enumoptional

Format of the transcription response

Default: verbose_jsonAvailable options:

temperatureany ofoptional

Sampling temperature for model responses (default is None).

Default: 0

timestamp_granularitiesany ofoptional

Granularities of timestamps to populate

filestring · binaryrequired

Responses

application/json

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://api.aibrary.dev/v0/audio/transcriptions' \
  --header 'Authorization: Bearer YOUR_SECRET_TOKEN' \
  --header 'Content-Type: multipart/form-data' \
  --form 'model=text' \
  --form 'language=text' \
  --form 'prompt=text' \
  --form 'response_format=json' \
  --form 'temperature=1' \
  --form 'timestamp_granularities=word' \
  --form 'file=binary'

200

422

200

{
  "text": "text",
  "task": "text",
  "language": "text",
  "duration": 1,
  "words": [
    {
      "word": "text",
      "start": 1,
      "end": 1
    }
  ],
  "segments": [
    {
      "id": 1,
      "seek": 1,
      "start": 1,
      "end": 1,
      "text": "text",
      "tokens": [
        1
      ],
      "temperature": 1,
      "avg_logprob": 1,
      "compression_ratio": 1,
      "no_speech_prob": 1
    }
  ]
}

Successful Response