Whisper Transcription API

Fast, accurate speech-to-text powered by Groq's Whisper Large v3

Endpoints

POST /v1/transcribe Transcribe an audio file

GET /health Health check

Quick Start

curl -X POST https://whisper.mythosvpn.net/v1/transcribe \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "[email protected]"

# Optional: specify language (ISO 639-1)
curl -X POST https://whisper.mythosvpn.net/v1/transcribe \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "[email protected]" \
  -F "language=en"

Response

{
  "text": "Hello, this is a transcription test.",
  "language": "en",
  "duration": 3.42,
  "segments": [ ... ]
}

Pricing

Free

$0 /mo
  • 10 requests per day
  • Max 10 MB file size
  • Whisper Large v3

Pro

$9 /mo
  • 100 requests per day
  • Max 50 MB file size
  • Whisper Large v3
  • Priority support
⭐ Buy via Telegram Stars — instant

or pay $9 USDT (TRC20):

TWPreCf98j8LmPqia7RNT8cJcMqWMoNFuD

After USDT payment: message @startuplabot with TX ID + API key. Activated within 1h.

Get Your Free API Key

No signup, no credit card. Instant key generation.

Authentication

Include your API key in every request via one of:

Use Cases

Python Example

import requests

with open("audio.mp3", "rb") as f:
    r = requests.post(
        "https://whisper.mythosvpn.net/v1/transcribe",
        headers={"X-API-Key": "YOUR_KEY"},
        files={"file": f}
    )
print(r.json()["text"])

n8n Integration

Use the HTTP Request node in n8n: