Custom Voiceover TTS Website Development

I need a web-based text-to-speech platform focused on one clear goal: letting users generate polished voiceovers for their videos, ads and social posts. The user flow should feel effortless. Visitors either paste their script into a text field or upload it as a document, pick the voice and language they like, fine-tune speed and pitch, choose their preferred output quality/format, then download the finished audio in seconds.

The site has to run smoothly on all modern browsers, so a clean front-end (React or similar) coupled with a solid back-end is essential. I am open to whichever cloud TTS engines or open-source models you feel give the best balance of realism, language coverage and cost efficiency; please outline your reasoning and any licensing factors when you bid.

Core deliverables
• Responsive UI/UX that handles the two input methods (paste text / upload script)
• Voice, language, speed, pitch and format selectors that update in real time
• Server-side generation of the audio plus secure, one-click download links
• Admin area where I can view usage metrics and add or remove available voices
• Deployment to my hosting of choice with clear hand-over documentation

The project is complete once a new user can land on the site, create a voiceover, download it and hear the selected settings reflected accurately in the audio. Looking forward to seeing your approach and timeline.