Hero Light

​
Transcribe Audio

VerbalisAI provides powerful audio transcription capabilities through our simple REST API. Convert speech to text with high accuracy using advanced AI models.

Try the API

Test our transcription endpoint with your own audio files

​
Quick Example

curl
# Download audio file
curl -L -o "audio.flac" "https://tinyurl.com/499rdjsh"

# Make transcription request
curl -X POST "https://api.verbalisai.com/api/audio/transcriptions" \
  -H "Authorization: <YOUR_API_KEY>" \
  -F "file=@audio.flac" \
  -F "model=whisper-v3"
python
import requests

# Transcribe audio file
with open("audio.flac", "rb") as audio_file:
    response = requests.post(
        "https://api.verbalisai.com/api/audio/transcriptions",
        headers={"Authorization": "YOUR_API_KEY"},
        files={"file": audio_file},
        data={"model": "whisper-v3"}
    )

transcription = response.json()
print(transcription["text"])

​
Request Format

The transcription endpoint accepts multipart form data with the following parameters:

​
Parameters

  • file (required) - The audio file to transcribe or URL to public audio file
    • Max file size: 1GB, no duration limit
    • Supported formats: mp3, flac, wav, m4a, ogg
    • Audio will be resampled to 16kHz mono before processing
  • model (optional) - Transcription model to use
    • Options: whisper-v3 (default), whisper-v3-turbo
    • whisper-v3: Higher accuracy, slower processing
    • whisper-v3-turbo: Faster processing, good accuracy

​
Key Features

Multiple Audio Formats

Support for MP3, FLAC, WAV, M4A, OGG and more audio formats

Advanced AI Models

Choose between accuracy-optimized and speed-optimized Whisper models

Large File Support

Process audio files up to 1GB with no duration limitations

Usage Analytics

Track your API usage and monitor transcription analytics

​
Getting Started

1

Create Account

Sign up for an VerbalisAI account to get access to the API
2

Get API Key

Generate your API key from the dashboard to authenticate your requests
3

Make Your First Request

Start transcribing audio files with our simple REST API

​
API Base URL

All API requests should be made to: 
https://api.verbalisai.com/api

​
Authentication

VerbalisAI API supports multiple authentication methods:
  • API Key Authentication: For secure API requests
  • Google OAuth: For social login integration

Authentication Guide

Learn more about authentication methods and how to secure your API requests

​
Support

Need help? We’re here to assist you:

​
Rate Limits

Our API includes rate limiting to ensure fair usage:
  • General API: 100 requests per 15 minutes per IP
  • Upload Operations: 20 requests per 15 minutes per IP
  • Authentication: 10 requests per 15 minutes per IP
Higher limits are available for enterprise customers.