Neurall API Docs (1.0.0)

Welcome to the Neurall API, your gateway to powerful AI-driven media generation, editing, and processing. Whether you're creating stunning visuals, enhancing media, or automating workflows, our API provides the tools you need to bring your ideas to life.

Getting Started

The Neurall API is designed for seamless integration and high performance. To begin, make sure to follow these key requirements:

  • Base URL: All API requests should be directed to: https://api.neurall.io

  • Secure Communication: All requests must be made over HTTPS. Any attempt to use plain HTTP will result in failure.

  • Authentication: Every request requires an API Key for authorization. You can manage API Keys in the Neurall app by navigating to Projects → API Keys.

Concurrency Limits

By default, each organization is limited to 100 concurrent API requests. This ensures optimal performance and reliability for all users. If your use case requires a higher concurrency limit, please contact our support team at support@neurall.io to request an increase.
All additional requests beyond this limit will return a 429 Too Many Requests error.

Next Steps

Explore our comprehensive endpoints, experiment with real-time AI-powered transformations, and start building with Neurall today!

Download OpenAPI description
openapi.json
openapi.yaml
Languages
Servers

https://api.neurall.io/

Images

The Images section provides endpoints for AI-powered image generation, enhancement, and manipulation.
These tools allow you to create, modify, and optimize images through a range of advanced processing techniques.

Operations

AI Cloning

The AI Cloning section provides endpoints for training and managing AI-generated clones of subjects. Using a set of images, you can train an AI Cloning model to replicate a subject's appearance.
Once the training is complete, generate new images by calling /v1/images/pegasus-generation and passing the identity_id parameter in the request.

Operations

Audio

The Audio section provides advanced speech processing capabilities. Convert spoken words into precise text transcriptions with accurate timestamps for each word, enabling seamless integration into captioning, analytics, and more.

Operations

Transcription

Request

Converts spoken audio into text and provides timestamps for each word.

Security
ApiKeyAuth
Bodymultipart/form-data
audiostring(binary)required

The audio file in MP3 format. The file size must not exceed 20MB, and the audio length should be a maximum of 5 minutes.

languagestring

The language of the speech. Must be one of the supported language codes. If a language is not specified, the API will try to autodetect the language based on the first 30 seconds of audio.

Enum"af""sq""am""ar""hy""as""az""ba""eu""be"
const axios = require('axios');
const fs = require('fs');
const FormData = require('form-data');

// Create form data
const form = new FormData();
form.append('image', fs.createReadStream('path/to/audio.mp3'));
form.append('language', '{{LANGUAGE}}');

// Make request
axios.post('https://api.neurall.io/v1/speech/transcription', form, {
    headers: {
        ...form.getHeaders(),
        authorization: '{{YOUR_API_KEY_HERE}}'
    }
}).then((response) => {
    console.log('Response received: ', response.data);
}).catch((err) => {
    console.error('Error in request: ', err);
})

Responses

Successfully generated transcription with word timestamps.

Bodyapplication/json
segmentsArray of objects
Response
application/json
{
  "segments": [
    { … }
  ]
}