I’m building a lightweight utility that takes plain text and generates natural-sounding audio files. The first release must speak both English and Hindi fluently; users should be able to switch between a male or female voice on demand. I’m open to whichever modern TTS engine or library you prefer—Amazon Polly, Google Cloud TTS, Coqui TTS, or an equivalent—so long as the final voice quality is smooth and human-like. Core scope • Input: pasted text or uploaded .txt/.docx file • Output: downloadable MP3 or WAV • Language toggle: English / Hindi (with room to plug in Spanish, French, or others later) • Voice selector: Male or Female • Simple GUI or clean CLI with clear usage instructions Deliverables 1. Fully working application (desktop, web, or cross-platform script) 2. Source code with concise README describing setup and how to add new languages/voices 3. Short demo clip proving both languages and both genders work Acceptance criteria: Audio plays end-to-end without glitches, pronunciation is accurate for common English and Hindi sentences, file export is under two clicks/commands. If this aligns with your skill set, let’s discuss the fastest path to a polished MVP.