Voice / Multimodal
VoiceForge
Real-time voice triage — ASR, LLM, TTS with latency budgets.
Browser-first ASR on Render free tier, pluggable LLM (mock / Ollama / DomainForge), edge-tts with browser fallback, per-phase latency waterfall, and graceful degradation to text.
In one sentence
Closes portfolio Pillar 5 — measurable ASR / LLM / TTS latency with honest free-tier defaults.
Decision
Browser ASR on Render; server Whisper opt-in on GPU hosts.
Measured signal
9-test CI · P50/P95 latency waterfall UI · phase budgets (ASR/LLM/TTS).
Honest limitation
Browser ASR quality varies; mock LLM default on Render until Ollama host wired.
- Browser Web Speech API ASR with client-reported latency
- Mock / Ollama / DomainForge LLM triage routes
- edge-tts server synthesis + browser speechSynthesis fallback
- REST and WebSocket transport with phase events
Architecture diagram
FastAPI · edge-tts · Next.js · Vercel · Render