Translation API

KrosAI's translation API allows you to translate text between multiple languages with high accuracy, especially for African languages.

This endpoint is OpenAI compatible

Overview

The API automatically detects the source language and translates content to your desired target language.

Endpoint

POST https://api.krosai.com/v1/audio/translations

This endpoint transcribes audio and translates it to English in one step.

Request Parameters

Parameter	Type	Required	Description
file	file	Yes	The audio file to transcribe and translate (mp3, mp4, wav, m4a, webm)
model	string	No	Model to use (default: "KrosMLingualSTT1.0.0")
prompt	string	No	Text to guide the translation
response_format	string	No	Output format (default: "json")
temperature	float	No	Model temperature (default: 0.0)

Example Request (cURL)

curl https://api.krosai.com/v1/audio/translations \
  -H "Authorization: Bearer $API_KEY" \
  -F file=@"recording.mp3" \
  -F model="KrosMLingualSTT1.0.0"

Response Format

{
  "id": "trans_1234567890",
  "object": "translation",
  "created": 1682456789,
  "model": "KrosMLingualSTT1.0.0",
  "text": "This is the translated text from the audio file.",
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 45,
    "total_tokens": 45
  }
}

Best Practices

Translation

• For multi-step translations, use the legacy endpoint

• Consider context when translating specialized content

• Test with small samples before processing large batches

Error Handling

All APIs return standard HTTP status codes:

• 200: Success

• 400: Bad request (check parameters)

• 401: Unauthorized (check API key)

• 429: Rate limit exceeded

• 500: Server error

Error responses include a detail field with more information about the error.