AI Assistant Voice Integration Needed

### Project Title: **Add Voice Output (Text-to-Speech or Speech-to-Speech) to Existing AI Assistant – Avatar Optional**

### Project Description:

We’ve already built a fully functional API-based assistant with a custom interface and secure authentication layer. What we now need is someone to **integrate a real-time voice engine** so the assistant can speak aloud in response to user prompts.

### What’s Already Done:

* Full assistant interface (React-based, HTML/CSS/JS version also available)
* Secure authenticator system (access control is implemented)
* Backend API integration with OpenAI (chat works perfectly)
* Visual design and assistant layout already complete

### What We Need:

1. **Voice integration (text-to-speech or speech-to-speech [preferably])**

* Preferably OpenAI (Important) TTS or Whisper-based
* Real-time or near-real-time speech output from assistant’s responses
* Should work smoothly in browser (Web Audio API)

2. **Optional: Avatar animation or visual reaction**

* Mouth movement synced to speech (ideal but not required)
* Simple animation that responds while talking

3. **Must work behind existing authentication system**

* No voice access unless user is logged in or authenticated

### Deliverables:

* Working voice-enabled assistant (browser-based)
* Configurable voice (female, warm tone preferred)
* All necessary scripts and configs to run locally or in Docker
* Documentation on how to modify/update the voice engine in the future

### Budget:

We are looking for **fixed-price bids in the range of \$250–\$500 USD**, depending on whether avatar sync is included.
Hourly is fine too, but we prefer fixed bids.

### Ideal Candidate:

* Experience with OpenAI APIs, Web Audio API, or TTS engines (Google, Azure, Coqui, etc.)
* Comfortable working with frontend frameworks or vanilla JS
* Bonus: Experience with avatar animation or Lottie integration

### Notes:

We will provide access to the assistant codebase and environment.
Everything else is ready — we just need your voice magic.