A standalone Windows desktop application for turning written scripts into natural-sounding multi-voice audio using OpenAI GPT for script refinement and ElevenLabs for voice generation.
T2V-v1 is a fully standalone Windows desktop application that converts scripts into polished, production-ready multi-voice audio outputs.
The workflow is built to simplify voice production from start to finish:
- Script refinement using GPT
- Automatic character extraction
- Voice mapping for each character
- Auto-memory for saved voice selections
- Multi-voice text-to-speech generation using ElevenLabs
- Final export in high-quality audio formats
This app is designed for animation creators, YouTubers, storytellers, voice content producers, and production teams who want a fast and consistent desktop workflow for voice generation.
T2V-v1 helps transform raw written content into final usable voice output through a structured pipeline:
- Refine the script for cleaner dialogue and narration
- Detect and extract characters automatically
- Assign voices to each speaker
- Reuse remembered voice mappings for faster future work
- Generate final mixed voice output
- Export professional-quality MP3 and WAV files
- GPT-based script refinement
- Automatic character extraction
- Voice selection and assignment per character
- Auto-memory for previously selected voices
- ElevenLabs text-to-speech integration
- Final mixed MP3 (320 kbps) output
- Final mixed WAV (48 kHz PCM) output
- Clean and focused desktop interface
- Standalone Windows workflow
Creating voice content manually can be slow and repetitive, especially when working with multiple characters or dialogue-heavy scripts.
T2V-v1 is built to make that process faster, cleaner, and more production-friendly.
Ideal for:
- Animation teams
- YouTube content creators
- Storytelling channels
- Dialogue-based projects
- Creative studios
- Voice-driven content production
The application generates high-quality final outputs suitable for content creation and production workflows:
- MP3 — 320 kbps
- WAV — 48 kHz PCM
These formats make the app suitable for both quick publishing and higher-quality editing pipelines.
- Desktop Windows application
- OpenAI GPT for script refinement
- ElevenLabs for text-to-speech generation
- Multi-character voice workflow
- Persistent voice memory system
T2V-v1 is useful for:
- Animated short videos
- Story narration
- Character dialogue generation
- Voice prototyping
- YouTube storytelling
- Content production pipelines
- Rapid audio draft creation
This project is intended for personal and individual use only.
By downloading or using this software/content, you agree to the following:
- Personal Use: You may use this for your own personal projects and enjoyment.
- No Redistribution: You may not re-upload, host, or redistribute these files on other platforms without explicit written permission.
- Commercial Use: Any use for profit, business, or commercial enterprise is strictly prohibited without a commercial license.
Contact: For commercial licensing inquiries or permission requests, contact GAMESBOND.
Built by Jash aka GamesBond
Powered by ElevenLabs and OpenAI GPT