🎙️

Audio Transcription API

Transcribe audio files to text using OpenAI Whisper. Supports MP3, WAV, OGG, WebM up to 25MB. Returns text, detected language, duration, and word segments.

API Docs $0.003 / minute

About this tool

Convert audio files to accurate text transcriptions using state-of-the-art Whisper AI models. Provide a URL to any publicly accessible audio file (mp3, mp4, wav, ogg, webm, m4a) up to 25MB. Returns the full transcription text, detected language, audio duration in seconds, and optional word-level segments. Pricing is based on audio duration at $0.003 per minute.

🧪 Try it live

Quick Start

curl -X POST https://api.iteratools.com/audio/transcribe \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com/audio.mp3", "language": "pt"}'

Response

{ "success": true, "text": "Olá, este é um exemplo de transcrição...", "language": "pt", "duration_s": 12.5, "segments": [...], "cost_usd": 0.001, "provider": "openai-whisper" }

Supported Formats

MP3 WAV OGG WebM M4A FLAC MP4

Details

EndpointPOST /audio/transcribe
Price$0.003 / minute of audio
Max file size25 MB
ProviderOpenAI Whisper (with Groq/Replicate fallback)
AuthBearer token or x402 micropayment
Base URLhttps://api.iteratools.com
Full Documentation Browse All Tools