Video Transcribe API — YouTube & MP4 to Text

About this tool

Transcribe any YouTube video or direct MP4/video URL to text using yt-dlp for audio extraction and OpenAI Whisper for transcription. Supports multiple output formats: plain text, SRT subtitles, or JSON with timestamps. Auto-detects language or accepts a specific language code.

Quick Start

curl -X POST https://api.iteratools.com/video/transcribe \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ", "language": "en"}'

Response

{
  "success": true,
  "text": "We're no strangers to love...",
  "language": "en",
  "duration_s": 212.5,
  "format": "text",
  "price_usd": 0.02,
  "provider": "openai-whisper"
}

Parameters

Parameter	Type	Description
url	string (required)	YouTube URL or direct MP4/video URL
language	string (optional)	Language code (auto, en, pt, es, fr, de…). Default: auto
format	string (optional)	Output format: `text` (default), `srt` (subtitles), `json` (with segments)

Pricing

$0.020 per video up to 30 minutes
$0.040 per video up to 2 hours
Payments via x402 micropayment on Base (USDC).