whisper-1 (audio translation)

POST

https://api.tokenhot.ai/v1/audio/translations

Actual API Endpoint: POST https://api.tokenhot.aiW1/audio/translations

Model Code: whisper-1

Request

Authorization

Body Params application/jsonRequired

Examples

Responses

🟢200

application/json

Request successful

Bodyapplication/json

🟠400400 en

🟠401401 en

🔴503503 en

Request Example

Shell

JavaScript

Java

Swift

curl --location 'https://api.tokenhot.ai/v1/audio/translations' \
--header 'Content-Type: application/json' \
--data-raw '{
    "file": "@binary_file_object",
    "model": "whisper-1",
    "prompt": "Optional: Prompt to guide translation",
    "response_format": "json",
    "temperature": 0
}'

Response Example

200 - Example 1

{
    "text": "Hello everyone, today we are demonstrating the translation capabilities of the Whisper model. It can accurately convert speech into English text."
}

Modified at 2026-05-29 02:58:01

gemini-2.5-pro-preview-tts

whisper-1 (Audio to Chinese)