Taniya Souza
Learn to explain the skills you vibe-code or learn to pitch your idea, visit this gym to work on your COMMUNICATION skills!
Core trick
Runs speech-to-text and text-to-speech through Sarvam while Gemini holds the live conversation and a skill graph stores per-session scores.
Description
Learn to explain the skills you vibe-code or learn to pitch your idea, visit this gym to work on your COMMUNICATION skills! gemma is gonna nudge you! I know everyone needs a practise esp in India where many of us need to accept that our technical skills are way ahead of our way to communicate.
README excerpt
# Proof of Synergy <img width="900" height="600" alt="image" src="https://github.com/user-attachments/assets/c298a1aa-ff46-4595-a1b5-d5f4949916b4" /> An AI communication gym. Practice real conversations by voice, get live coaching, and build a skill graph that persists across sessions. Includes a resume-based technical interview mode. ## Stack Next.js 14 (App Router), React 18, TypeScript, Tailwind. OpenTelemetry is used for optional end-to-end tracing. Gemini is the live conversation partner; Sarvam handles voice (speech-to-text, text-to-speech) and coaching summaries. Cognee is an optional semantic layer for the skill graph. Everything degrades gracefully: with no keys the app runs on a local conversation partner, heuristic coaching, and the built-in skill-graph engine. ## Run ```bash npm install npm run dev # http://localhost:3000 ``` Other scripts: `npm run build`, `npm start`, `npm test`, `npm run test:watch`, `npm run typecheck`, `npm run check` (typecheck + test), `npm run voice-gateway` (standalone WebSocket signaling server for realtime voice sessions, see `server/voice-gateway.ts`). ## Config Copy `.env.local.example` to `.env.local` and add your keys. Everything is optional; the app degrades gracefully without keys. ``` GEMINI_API_KEY= # live conversation partner (dialogue, follow-ups, pushback) SARVAM_API_KEY= # voice: STT, TTS, resume OCR, and coaching summaries COGNEE_API_URL= # optional skill-graph semantic layer COGNEE_API_KEY=