TranscriptFetch's answer

It started with discovering there is no good way to get the text of a video. YouTube’s official Data API will confirm a caption track exists and then refuse to hand it over, because captions.download requires the video owner’s OAuth token. The popular open-source libraries work until you deploy them, at which point platforms start refusing datacenter IPs. And YouTube is the easy case: TikTok and Instagram publish no caption file at all. Every workaround solved one platform, worked locally, and broke in production. TranscriptFetch is the version that handles the failure cases as first-class behaviour rather than edge cases.

Typer's answer:

In February 2026, ChatGPT started showing ads to free users and made $100 million in six weeks. That was the moment it became clear that free AI chat comes with a price - your attention, your data, or both. Typer started as a personal project: what if AI chat just ran on your Mac? No cloud, no account, no strings attached. Built solo over the past year with Tauri and Rust, designed to work the moment you open it. The goal was to make local AI as simple as opening any other app on your Mac. No terminal commands, no model configuration, no technical knowledge needed. Just ask your Mac anything.

TranscriptFetch's answer

Most short-form video has no caption track to download. TikTok’s auto-captions are opt-in per upload, Instagram never publishes a downloadable track, and many captions on both are burned into the video frames where no parser can read them. TranscriptFetch transcribes the audio when no caption track exists, on the same endpoint, with the same response shape. Your code never branches on which method produced the text. It also covers YouTube, TikTok, Instagram, X and Facebook plus any web page as clean Markdown, so a pipeline spanning several sources is one integration rather than five.

Typer's answer:

Typer is the only AI chat app that combines fully local, on-device AI with private web search. Every other local AI tool is either completely offline or completely cloud-based. Typer bridges both - you get AI that runs on your Mac with zero internet required, but when you need it, web search works locally too without sending your queries to external servers. There's no account, no cloud, no ads, and no token limits. It auto-detects your Mac's specs and picks the right AI model for your hardware, so there's zero setup.

TranscriptFetch's answer

Three reasons. Coverage: one API key and one response shape across five video platforms and the open web, instead of stitching together a library per platform. Reliability: requests run through rotating infrastructure, so code that works locally keeps working from a server, which is where most open-source approaches break. Billing that matches reality: one credit per successful response, with failed, blocked and empty results never charged. That last point matters on short-form video, where a meaningful share of any batch is music with no speech in it. There is also an MCP server, so AI agents can fetch transcripts as a tool without a custom integration.

Typer's answer:

• Zero setup - Typer detects your hardware and picks the right AI model automatically. No configuration, no downloading models manually, no terminal commands
• No ads - ChatGPT started showing ads to free users in February 2026. Typer will never show ads
• No account required - most competitors need you to sign up and hand over personal data before you can use them
• Completely free with no token limits - ChatGPT, Claude, and Gemini all cap free usage. Typer doesn't
• Works offline - take it on a plane, use it on the train. No internet needed
• Private by design - conversations never leave your Mac. There's no server to send data to
• Web search that stays private - when you do need the web, Typer searches without sending queries to external servers. No other local AI tool does this

TranscriptFetch's answer

Developers and technical teams building on video and web content. The common cases are RAG and retrieval pipelines that need video as text, AI agents that need to read a link mid-conversation, content teams repurposing short-form video at scale, and media monitoring and research tools. It is an API first, so the buyer is usually the person writing the integration rather than an end user. The free browser tools exist for one-off transcripts and for evaluating output quality before writing any code.

Typer's answer:

Mac users who want AI chat without the complexity. People who use ChatGPT but are tired of token limits, ads, and handing over their data. They don't care about model names or benchmarks - they just want to ask their Mac a question and get a good answer. Privacy-conscious users who don't want their conversations stored on someone else's server. People who travel or work offline and need AI that works without internet. Anyone with an Apple Silicon Mac who wants a simple, free, private AI assistant.

TranscriptFetch's answer

Next.js with TypeScript and Tailwind on the front end and API layer, Clerk for auth with SHA-256 hashed API keys, Neon Postgres with Drizzle ORM, Redis for caching, and Stripe for billing. The extraction layer is a Python and FastAPI service. Speech-to-text uses Whisper-class models. The MCP server is published in the official Model Context Protocol registry with a DNS-verified namespace.

Typer's answer:

• Tauri v2 - native desktop framework, no Electron bloat
• Rust - backend and core application logic
• llama.cpp - local LLM inference engine via llama-cpp-rs bindings
• Apple Metal - GPU acceleration on Apple Silicon for fast AI processing
• HTML, CSS, JavaScript - lightweight frontend with no framework
• ChaCha20-Poly1305 - encryption for locally stored conversations

Typer's answer:

Typer is a free consumer app, not an enterprise product. It doesn't have "customers" in the traditional sense. Its users are individual Mac owners who want private, local AI chat without accounts or subscriptions.