AI-Powered Interactive Avatar Development

We are developing an AI-powered interactive avatar designed to engage users through real-time voice conversations, natural animation, and emotional responses. Our goal is to create a character that feels alive, entertaining, and deeply interactive.

?️ Core Responsibilities:
Set up API integration with ChatGPT, ElevenLabs, and D-ID
Build backend logic that handles:
Text + voice input from the user

What You'll Build:
The system should allow users to:
Send a voice message or text input
Convert voice to text using OpenAI Whisper (or a better speech-to-text API)
Send text to ChatGPT (via OpenAI API)
Convert ChatGPT's response to audio using ElevenLabs
Stream the audio + text to D-ID for real-time avatar lip-sync and facial animation
Whisper speech-to-text
Response generation and audio output
Clean data flow to D-ID for avatar rendering

✅ Skills You Must Have:
Strong experience with API integrations (REST, streaming, JSON payloads)
Comfortable working with OpenAI, ElevenLabs, and preferably D-ID SDK
Knowledge of audio processing, WebRTC or media pipelines (bonus)
Node.js or Python expertise
Experience with cloud functions, backend logic, and third-party services
Able to work fast, communicate clearly, and collaborate to build something magical