Whisper V3 Turbo

Convert speech to text using advanced AI models with recording or file upload options

Backend online

🎤

Record Audio

Click to start recording your voice

📁

Upload File

Upload an audio file for transcription

Ready to record

🔌 API Access

Transcribe audio files programmatically with our REST API.

🔑 API Keys

To use the API, you need an API key. Manage your API keys →

POST /api/v1/generate

Transcribe Audio with Whisper ASR

Send recorded audio and receive transcriptions powered by Whisper Large V3 Turbo.

Cost: 0.0009 credits per audio minute

Include duration_seconds so billing reflects your recording length.

Request (cURL)

curl -X POST https://app.eigenai.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=whisper_v3_turbo" \
  -F "file=@/path/to/audio.mp3" \
  -F "language=en" \
  -F "response_format=json"

Request (Python)

import requests

url = "https://app.eigenai.com/api/v1/generate"
headers = {"Authorization": "Bearer YOUR_API_KEY"}

with open("speech.mp3", "rb") as audio:
    files = {"file": ("speech.mp3", audio, "audio/mpeg")}
    data = {
        "model": "whisper_v3_turbo",
        "language": "en",
        "response_format": "json"
    }

    response = requests.post(url, headers=headers, data=data, files=files)

    # Print status code and response
    print(f"Status Code: {response.status_code}")
    if response.status_code == 200:
        print(response.json())
    else:
        print(f"Error: {response.text}")

Request (JavaScript/Node.js)

const FormData = require('form-data');
const fs = require('fs');
const axios = require('axios');

const form = new FormData();
form.append('model', 'whisper_v3_turbo');
form.append('file', fs.createReadStream('audio.mp3'));
form.append('language', 'en');
form.append('response_format', 'json');
form.append('duration_seconds', '60');

axios.post('https://app.eigenai.com/api/v1/generate', form, {
    headers: {
        ...form.getHeaders(),
        Authorization: 'Bearer YOUR_API_KEY'
    }
}).then(response => {
    console.log(response.data.text);
});

Parameters

Parameter	Type	Required	Description
`model`	string	✅ Yes	Must be `asr`
`file`	file	✅ Yes	Audio input to transcribe (MP3, WAV, M4A, OGG, WebM)
`language`	string	Optional	Spoken language code (default `en`)
`response_format`	string	Optional	Desired output format (`json`, `text`, etc.)

Transcription Result

🎯

Your transcription will appear here

Cost: 0.0009 credits per audio minute.