Can We Trust It's answer

It gives an honest, probabilistic read — it flags high-risk patterns and explains the reasoning in plain language, rather than claiming certainty that something "is" a scam. There's no account, no upsell, and no security-suite bloat: you paste a suspicious email, text, link, or screenshot and get a clear risk check in seconds. It works in 20 languages with full right-to-left support, and it's backed by 50+ in-depth guides on specific scams.

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.

Can We Trust It's answer

It started when the founder's mother nearly fell for a fake delivery text. That moment — seeing how convincing modern scams have become, and how little quick help exists for someone in the moment of doubt — was the motivation. Can We Trust It was built solo as both a product and a personal mission: an honest, no-account tool that gives people a fast, plain-language read on whether a message is safe.

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.

Can We Trust It's answer

Most scam-checkers are free loss-leaders that require an account and funnel you toward a paid security suite. Can We Trust It does one thing well: check a message, fast, free, no sign-up. The verdicts are deliberately probabilistic and transparent about their reasoning, it supports 20 languages including right-to-left scripts, and it's privacy-first — no account, and message content isn't stored. It's built for the moment you've just received something suspicious and want a quick, honest second opinion.

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.

Can We Trust It's answer

Everyday people at the moment they receive something suspicious — a text, email, job offer, listing, or social message they're unsure about. It's especially for the people scammers target most, including those less familiar with the latest tactics. The 20-language, right-to-left support also makes it useful for non-English speakers, who are often underserved by English-only tools.

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.

Can We Trust It's answer

Next.js (App Router) with TypeScript and Tailwind CSS, deployed on Vercel. Scam analysis is powered by large language models via the Anthropic Claude API, including image analysis for screenshot uploads. It uses Upstash Redis for rate limiting, Stripe for payments, and next-intl for 20-language internationalisation with right-to-left support.

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.