Or jump from this list on a smaller screen.
This is a page from the Audivra documentation. Developer exports — index: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.
Deploy
Production deployment with Supabase, Docker Compose, Caddy TLS, and Celery workers.
SaaS (Next.js) — Studio, playground, STT, dub, voices, agents, keys, billing
Gateway (FastAPI :8080) — Auth, rate limits, Celery queue, generate/batch/estimate
Inference (:8090 / Modal) — Kokoro/F5 TTS → MuseTalk lip-sync → FFmpeg MP4; fast-path local <500 chars
Data — Supabase Postgres + RLS, Redis, object storage CDN
Production checklist
Deploy
cp .env.example .env # Fill SUPABASE_*, STRIPE_*, S3_*, REDIS_URL, MODAL_* keys # Serverless (Lambda): NEXT_PUBLIC_SUPABASE_URL + SUPABASE_SERVICE_ROLE_KEY are required; # do not rely on .data/store.json (/var/task is read-only). supabase db push # 0001–0018 plus timestamped reviews/KYC/consent files ./scripts/backup-ops.sh # JSON store + supabase db dump when linked curl -sf http://127.0.0.1:3000/api/health ./deploy.sh # validates env + starts docker-compose.prod # Or local full stack: docker compose up --build
Services
Processes
npm run dev # Next.js dashboard :3000 npm run gateway # FastAPI :8080 npm run celery:worker # async GPU jobs npm run inference # local GPU :8090 npm run inference:modal # serverless T4 scale-to-zero
Verify install
CI-style checks
npm run verify:all
B2B private cloud, SLA, and air-gapped options: Enterprise & private deployment