This demo app uses Whisper and LLaMA to transcribe audio files and generate summaries. You can use the building blocks of this app to create your own AI apps. Includes complete source code and documentation.
Integrations with OpenAI, Anthropic, xAI, Groq, Replicate, Elevenlabs and more
Landing pages, UI Components, Input Forms, Response Display
API Routes, Auth, Rate limits, Tool Calls, JSON Schemas, Scraping tools
Supabase auth & database, RAG & vector embeddings, Emails, Storage
Stripe/LemonSqueezy, Credit-based usage limits
PostHog, Meta Tags, Sitemap, Programmatic SEO-ready
Chat, Text, Vision, Audio, PDF Analysis, Image Generation & more
Estimated time saved compared to building from scratch
app/(apps)/audio/(app)/*
React Components, TailwindCSS, shadcn/ui
app/api/(apps)/audio/*
Next.js API Routes for file uploads, transcription, summarization, deletion + Cloudflare R2 & Supabase Integration
app/(apps)/audio/*
Prompts, Audio Processing, Transcription Logic