Voicecore.ai

Enterprise-Grade Features

✨

No Rate Limits

Self-hosted infrastructure means unlimited transcription capacity. Scale as much as you need.

🌍

Multi-Language

Hebrew, English, and 90+ languages supported. Automatic language detection included.

🔒

Privacy First

Your data stays on your servers. Complete control over sensitive audio and transcripts.

⚡

Lightning Fast

📊

99.9% Uptime

Enterprise-grade reliability with automatic failover and health monitoring.

💰

Predictable Pricing

No per-minute costs. Fixed monthly pricing regardless of usage volume.

Technical Specifications

Model

OpenAI Whisper Large-v3

Languages

90+ (Hebrew, English, Arabic, Spanish, etc.)

Supported Formats

MP3, WAV, M4A, FLAC, OGG, WebM

Max File Size

100 MB per file

API Type

REST/JSON

Authentication

None required (can be added)

API Documentation

Use the Whisper API directly from your code

Endpoint: POST http://199.68.217.31:60582/transcribe

Note: This is a direct API endpoint. Call it from your backend code (Python, Node.js, etc.) — not from browser JavaScript.

Quick Start Examples

cURL

Python

JavaScript (Node.js)

Response

# Basic transcription
curl -X POST http://199.68.217.31:60582/transcribe \
  -F "file=@audio.mp3" \
  -F "language=auto"

# Transcribe with specific language
curl -X POST http://199.68.217.31:60582/transcribe \
  -F "file=@hebrew_audio.wav" \
  -F "language=he"

import requests

url = "http://199.68.217.31:60582/transcribe"
files = {"file": open("audio.mp3", "rb")}
data = {"language": "auto"}

response = requests.post(url, files=files, data=data)
result = response.json()

print(f"Text: {result['text']}")
print(f"Language: {result['language']}")
print(f"Duration: {result['duration']} seconds")

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

const form = new FormData();
form.append('file', fs.createReadStream('audio.mp3'));
form.append('language', 'auto');

axios.post('http://199.68.217.31:60582/transcribe', form, {
  headers: form.getHeaders()
})
.then(res => console.log(res.data))
.catch(err => console.error(err));

// Successful response
{
  "text": "Transcribed text here",
  "language": "en",
  "duration": 2.5
}

Parameters

file — Audio file (mp3, wav, m4a, ogg, flac)
language — Language code (en, he, ar, etc.) or "auto" for auto-detect

Supported Languages (90+)

en English • he Hebrew (עברית) • ar Arabic (عربي) • es Spanish • fr French • de German • it Italian • pt Portuguese • ru Russian • ja Japanese • ko Korean • zh Chinese • and 80+ more

Batch Processing Example

# Process multiple audio files (Python)
import requests
import os
from pathlib import Path

API_URL = "http://199.68.217.31:60582/transcribe"

def transcribe_file(file_path, language="auto"):
    with open(file_path, 'rb') as f:
        files = {'file': f}
        data = {'language': language}
        response = requests.post(API_URL, files=files, data=data)
        return response.json()

# Process all audio files in a folder
audio_folder = Path("./audio_files")
for audio_file in audio_folder.glob("*.mp3"):
    print(f"Processing: {audio_file.name}")
    result = transcribe_file(audio_file)
    print(f"  → {result['text']}\n")

Live Demo

Demo Currently Unavailable