Syed Naazim Hussain

SPELLSPEAK is a voice-driven magic battle game where your vocabulary is your weapon. There are no buttons and no predefined spell list — you describe a spell out loud, and the game generates everything in real time. It uses 7 ElevenLabs APIs deeply integrated across the entire battle loop: • Scribe v2 for speech-to-text transcription of player spells • SFX V2 for generating unique spell sound effects from text • Eleven v3 + Audio Tags for emotional enemy wizard voice responses • Voice Design for procedurally generating a unique villain voice each session • Eleven Music for archetype-matched battle soundtracks • Music Inpainting for injecting orchestral critical-hit stings into the live track The AI scores every spell on creativity, specificity, coherence, and drama — a boring "fireball" loses to "a tornado of frozen glass shards that screams at the frequency of breaking bones." The enemy wizard analyzes your spell, taunts you with emotional voice acting, and counters with its own generated magic. Built entirely in Zed with Gemini Flash for spell scoring and image generation. No two battles ever sound or look the same.

Submitted 30 Apr 2026

FieldBrieff is a voice-first AI assistant for field workers — electricians, plumbers, HVAC techs, and construction crews — who need code-compliant answers on the job without touching a screen. On a worksite, stopping to search isn’t practical. Hands are busy. Gloves are on. Time matters. With FieldBrieff, workers just ask a question by voice and get a cited, authoritative answer in under 8 seconds. Powered by ElevenLabs Conversational AI, it handles the full voice loop — real-time speech-to-text, multi-turn reasoning, and natural voice responses — creating a seamless, hands-free experience. To ensure accuracy, the system uses Firecrawl Search to retrieve live information from trusted sources like NFPA, OSHA, and ASHRAE, ranking results by domain authority instead of SEO, and returning answers with proper citations. FieldBrieff also introduces a Photo Query mode: Point your camera at equipment — a breaker, panel, junction box, or pipe — and Gemini Vision identifies specs like ratings, wire gauges, and model numbers. This context is injected into the voice session, so the AI answers with full situational awareness. What makes it truly powerful: It works over a simple phone call. Workers can dial a number — no app, no login, no internet — and instantly access the same AI assistant via PSTN using Twilio. Even a basic phone becomes a real-time expert. No screens. No interruptions. Just answers.