Gladia API Documentation

Overview

Gladia provides a suite of AI-powered communication APIs for voice, video, and chat. Our platform allows developers to integrate real-time speech-to-text transcription, video analytics, and intelligent conversation models into their applications. This documentation guide will help you get started with integrating and using Gladia's APIs.

Getting Started

To begin using the Gladia API, you need an API key. You can obtain one by signing up on our website. Once you have your API key, you can include it in your requests for authentication.


                                curl -X POST https://api.gladia.com/v1/voice/transcribe \
                                     -H "Authorization: Bearer YOUR_API_KEY" \
                                     -F "file=@your-audio-file.wav" \
                                     -F "language=english"

Replace YOUR_API_KEY with your actual API key. Supported file formats include WAV, MP3, and PCM.

API Reference

Below are the key endpoints available in the Gladia API:

Voice Recognition

Convert speech to text with high accuracy.

POST /api/v1/voice/transcribe multipart/form-data

Parameter	Type	Description
file	file	Audio file to transcribe
language	string	Language of the audio
model	string	Speech-to-text model to use

Video Analytics

Analyze video content with AI-driven insights.

POST /api/v1/video/analyze multipart/form-data

Currently, video analytics requires file upload similar to voice recognition.


                                    curl -X POST https://api.gladia.com/v1/video/analyze \
                                         -H "Authorization: Bearer YOUR_API_KEY" \
                                         -F "video=@your-video-file.mp4"

Authentication

All API requests must be authenticated with a Bearer token. Include your API key in the Authorization header:


                                Authorization: Bearer YOUR_API_KEY

You can find your API key on your account page. Keep it secure and avoid sharing it publicly.

Examples

Here are example integrations using Gladia's API in different programming languages.

JavaScript (Node.js)


const fetch = require('node-fetch');
const form = new FormData();
form.append('file', fs.createReadStream('audio.wav'));
form.append('language', 'english');

fetch('https://api.gladia.com/v1/voice/transcribe', {
  method: 'POST',
  body: form,
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  }
})
.then(response => response.json())
.then(data => console.log(data));

Python


import requests

url = 'https://api.gladia.com/v1/voice/transcribe'
headers = {'Authorization': 'Bearer YOUR_API_KEY'}
data = {'language': 'english'}
files = {'file': open('audio.wav', 'rb')}

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