Overview

AI Text-to-Video API enables the seamless transformation of textual input into dynamic, visually rich videos using advanced AI and machine learning. It processes text using NLP to understand context and sentiment, generating realistic or animated scenes, character animations with lip-syncing, and synchronized voiceovers. The API supports customization of styles, transitions, branding, and sound effects, while offering multi-language support and real-time rendering.

Getting Started

1. Get Available Voices

   First, retrieve the list of available voices by making a GET request to:

   GET https://mango.quickreel.io/api/v2/constants/voices
   

   This will return over 800 voices with their details including:

   • voiceId (required for next step)
   • name
   • gender
   • languageCode
   • style
   • sampleVoiceUrl

   For Getting the list of voices, Please refer to the Voices Page.

2. Create Text-to-Video Request

   Send a POST request with your configuration:

   Base URL: https://mango.quickreel.io/api/v2

   Endpoint: /ttv

   Method: POST

   Headers:

   Content-Type: application/json
   x-api-key: <your_api_key>
   

   Request Body Parameters

   Key	Type	Description	Required
   voiceId	STRING	Voice ID from step 1 (e.g., “386a7b80-1001-4017-bb51-49b3428ab8f4”)	Yes
   script/prompt	STRING	Either provide a script directly or a prompt to generate content	Yes (one of them)
   webhookUrl	STRING	URL to receive processing updates	Yes
   visualStyle	STRING	Visual style for video generation (see options below)	No
   subtitleStyles	OBJECT	Customize subtitle appearance	No
   additionalFeatures	OBJECT	Additional processing options	No

   Subtitle Styles

   • template (STRING): Subtitle template style. Default is “productive”. Options include “none”, “harmozi”, “pulse”, “filler”, “whisperer”, “marineShift”, “sonic”, “spotlight”, “focusFlash”, “inflate”, “boxd”, “productive”, “beast”, “impact”, “fade”, “typewriter”.
   • position (STRING): Position of subtitles on the video. Default is “bottom-center”. Options include “bottom-center”, “top-center”, “middle-center”.
   • fontSize (STRING): Font size for subtitles. Default is “m”. Options include “s”, “m”, “l”, “xl”.

   If you want to see preview of the subtitle styles, you can go to the AI Subtitle Page.

   Visual Style Options: (STRING):Visual style for video generation. Default is “realism”. Options include “realism”, “anime”, “cyberpunk”, “comic”, “fantasy”, “scifi”, “lego”, “pixel_art”, “line_art”, “renaissance”, “medieval_painting”, “wes_anderson”, “anime_figures”, “porcelain”.

   If you want to see preview of the visual styles, you can go to the Visual Style Page.

   For optimal results, we recommend: - Maximum script length of 100 words per request - Clear, well-structured prompts - High-quality reference materials when needed

   Example Request:

   {
     "voiceId": "386a7b80-1001-4017-bb51-49b3428ab8f4",
     "script": "Your video script content here",
     "webhookUrl": "https://your-webhook-url.com",
     "visualStyle": "realism",
     "subtitleStyles": {
       "template": "productive",
       "position": "bottom-center",
       "fontSize": "m"
     },
     "additionalFeatures": {
       "addBgm": false
     }
   }
   

Response

Upon successful processing, the webhook URL will receive a response with the status and details of the processed video. The response includes metadata about the clip, such as duration, resolution, and a direct link to download the processed video.

Advanced Features & Capabilities

AI Script Generation

Transform simple prompts into engaging video scripts using advanced language models. Perfect for quick content creation without writing detailed scripts.

Visual Style Customization

Choose from 15+ unique visual styles including realism, anime, cyberpunk, and more to match your brand aesthetic and content theme.

Smart Subtitle Generation

Automatic subtitle generation with 16 customizable templates and multiple positioning options for maximum viewer engagement.

Multi-Voice Support

Access to 800+ AI voices across different languages, accents, and styles for perfect narration matching.

Use Cases & Applications

Marketing

• Product demonstrations - Social media content - Brand storytelling - Educational content

Education

• Course materials - Tutorial videos - Learning resources - Student guides

Business

• Training videos - Company presentations - Client communications - Internal updates

Best Practices

Tips for Optimal Results

• Keep scripts concise and focused for better visual generation - Test different visual styles with sample content first - Use appropriate voice styles matching your content tone - Consider your target platform when selecting video dimensions - Leverage subtitle templates for better engagement

Performance & Limitations

Processing Time

Average processing time varies based on: - Script length - Visual style complexity - Selected features - Queue status

Quality Assurance

Each video undergoes: - Visual quality checks - Audio sync verification - Subtitle alignment - Performance optimization

Need Advanced Support?

Join our Discord community for: - Technical assistance - Feature requests - Best practice sharing - Community tips and tricks