Audio Transcription

Create an audio transcription

post

This endpoint transcribes audio into the input language using the specified model.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

multipart/form-data

A request object for generating audio transcriptions and controlling router behavior. This object contains suggested parameters to generate a response from the specified model. Many of the parameters are optional, and it is recommended to set them only if needed; however, you may include other parameters as required. Note that not all providers support the same set of parameters. Adding unsupported or unnecessary parameters can cause requests to fail or limit the providers able to process them.

filestring · binaryRequired

The audio file object to transcribe.

modelstringRequired

The model to use for the transcription.

Example: whisper-large-v3

languagestring · nullableOptional

The language of the audio input, following ISO-639-1 format such as en for English, fr for French, de for German.

Example: en

promptstring · nullableOptional

An optional text to guide the model's style.

response_formatstring · nullableOptional

The format of the transcript output.

Example: json

temperaturenumber · nullableOptional

Controls randomness in the output. Higher values make the output more random.

preferencestring · enumOptional

The provider preference for handling the request.

Default: balancedPossible values:

allowed_providersstring[] · nullableOptional

The providers that are allowed to be used for the transcription.

Example: ["ovh","scaleway"]

eu_nativeboolean · nullableOptional

Whether to consider only providers based and regulated within the EU. Even when false, all our endpoints are GDPR compliant.

Default: falseExample: false

allow_quantizationboolean · nullableOptional

Whether to allow quantized endpoints.

Default: trueExample: true

Responses

200

OK

application/json

idstringOptional

The unique identifier for the transcription

Example: 1234567890

objectstringOptional

The type of object returned

Example: audio.transcription

createdintegerOptional

The timestamp when the transcription was created

Example: 1715155200

providerstringOptional

The provider that generated the transcription

Example: ovh

modelstringOptional

The model that generated the transcription

Example: whisper-large-v3

textstringOptional

The transcribed text.

languagestring · nullableOptional

The language of the audio input.

Example: en

segmentsobject[] · nullableOptional

Segments of the transcribed text (may be unavailable for some providers).

500

Internal server error.

post

/audio/transcriptions

PythonJavaScriptcurl

import requests

url = "https://api.cortecs.ai/v1/audio/transcriptions"
audio_file_path = "path/to/audio_test.mp3"

headers = {
  "Authorization": "Bearer YOUR_SECRET_TOKEN"
}

files = {
  "file": open(audio_file_path, "rb")
}

data = {
  "model": "whisper-large-v3",
  "language": "en",
  "allowed_providers": '["ovh", "scaleway"]',
  "eu_native": "false"
}

response = requests.post(url, headers=headers, files=files, data=data)
print(response.json())

{
  "id": 1234567890,
  "object": "audio.transcription",
  "created": 1715155200,
  "provider": "ovh",
  "model": "whisper-large-v3",
  "text": "text",
  "language": "en",
  "segments": [
    {}
  ],
  "usage": {
    "audio_duration_seconds": 18
  }
}

Additional parameters may be included; ensure they are supported by the selected provider by consulting the documentation.