Everything between “something happened” and “upload”
VidiScoop is not a trend list and not a prompt box. It is a research engine that understands which channel you are planning for, and a packaging engine that writes for that channel specifically.
Most tools show you what is trending on the internet. VidiScoop answers a narrower and far more useful question: what happened in the last day that is worth a video on this channel.
Multi-source discovery
Google News search feeds scoped to exactly the last 24 hours, Google News topic sections, curated outlet feeds chosen for your sections and region, regional Google Trends, and, on Creator and Studio, any RSS feed you paste in yourself.
Duplicate collapsing
Twelve outlets reporting the same event become one story with a coverage count of twelve — which is itself one of the strongest signals that a story is real and breaking wide.
Rarity-weighted relevance
A keyword like “movie” matches everything and is worth almost nothing. A keyword like “x-men” matches the thing you actually cover. Relevance weights each keyword by how rare it is across the scan.
Exponential freshness decay
Freshness does not fall off a cliff at a fixed hour — it decays continuously, so a 40-minute-old story is meaningfully ahead of a four-hour-old one instead of both being “today”.
Trend confirmation
Regional Google Trends is checked as a separate signal, so a story that is quietly reported but loudly searched still surfaces.
Source authority
A wire service carries more weight than an aggregator republishing it. Authority is a small but decisive tiebreaker between two otherwise identical stories.
YouTube competition check
Checks how many videos already exist for each top story and adjusts its score for how crowded the topic is, so you can tell an open lane from a crowded one. Uses your own YouTube Data API key; Creator and Studio.
Breakouts
Competitor videos pulling well above that channel’s normal for their age, on topics your feeds did not pick up — grouped by topic across channels and flagged when still climbing. Part of competitor tracking on Studio.
Scheduled scans
Each channel can rescan itself on an interval you set, and package any story above a score you choose while you are away. “Scan all channels” refreshes every channel in one press. Creator and Studio.
Want to see the judgement behind these signals without the software? The guide on how the scoring method works in practice runs the same five questions by hand on real story types.
Packaging & workflow
Turn the decision into an upload
Choosing the story is half the job. The other half is the title, the description, the tags and the thumbnail — and that is where most channels quietly lose their views.
Full video packages
Five titles, a description, tags, hashtags and five thumbnail briefs, one per title, each with the words to put on the thumbnail — written for a long-form video from the story and your channel’s positioning, not from a generic template.
Never a competitor’s title
A suggested title that is a near word-for-word copy of a competitor’s video title is dropped before you see it, and older packages flag any that slipped through.
Bulk packaging, quickly
Tick stories or breakouts, or use the Top 5, Top 10 and All quick picks for the best ones still without a package, and the selection bar generates up to 50 at once. “Package today’s top N”, with N set in Settings, scans and packages the day’s best in one click. Creator and Studio.
Story photos
Find images pulls the photos from the story’s own outlet pages and searches Wikimedia Commons and Openverse — plus Pexels and Pixabay with their free keys — showing each image’s real pixel size and licence.
NotebookLM, ready to paste
Your channel’s NotebookLM audio prompt with the chosen title already filled in — and the story’s source links too, wherever the prompt asks for them.
Follow-up detection
A story you already covered that resurfaces with nothing new goes to “Already covered”. If it genuinely develops, it comes back to the main list flagged as an update.
Per-channel workspaces
Niche, keywords, language, region, sections, custom feeds and minimum score are all set per channel. Switching channels switches everything.
Export and titles.txt
titles.txt puts the day’s chosen title for every channel in one file, on every plan. On Creator and Studio, CSV and Markdown export hands packages to a writer or editor who has no account.
A score nobody checks is a guess. Once a video is live you link it back in one step, and the numbers it earns tell you whether the call was right — then feed into how the next package for this channel gets written and ranked.
Link the video you published
Upload on your own channel, then paste the link — or connect YouTube read-only once and pick it from a list. Either way the video attaches to the story it came from, which is what makes everything below possible.
Post-publish analytics
Views, likes, comments, impressions, click-through rate, average view percentage and subscribers gained are pulled back per package, so you can check whether the must-cover stories actually outperformed.
Full script generation
A complete script drafted from the sourced description, with chapters estimated and timed automatically — a starting point to edit into your own voice, not a template to read verbatim.
AI fact-checking
Every claim in a generated script is checked against the original reporting it was built from and flagged as supported, partially supported or unsupported before you record.
AI thumbnail images
Beyond the brief: generate the actual thumbnail image from the shot and text-overlay description, with policy-safe prompts, through OpenAI, Gemini, OpenRouter or Runware, then download it directly. Creator and Studio.
◔
It learns what your channel wins with
Measured videos build a house style and a score calibration for your channel specifically — which title patterns earn clicks, which verdicts actually outperform — and later packages get ranked against that instead of a generic rule.
Beyond the single package
Channel intelligence — reads your channel’s own upload history to suggest sharper keywords and flag topics you have already covered.
Competitor tracking (Studio) — the channels you name feed the Breakouts view, and the Competitors tab adds the keyword gap between you and them, a weekly AI report and suggested competitors you may have missed.
Client share links (Studio) — a read-only, no-login view of a channel’s packages for a client or an editor who should not have workspace access.
Daily digest (Creator and Studio) — one morning email with the stories worth covering, so a scan is waiting for you instead of being something you remember to run.
Bring your own engine
Four AI providers, or none
The built-in engine runs the whole product with no API key at all. Add a key and the model re-reads every story in your channel’s context to sharpen the ranking, and writes the packaging properly instead of filling a template.
Google Gemini — has a free tier, the easiest place to start.
Claude — strongest at nuanced editorial judgement.
OpenAI — familiar, widely available.
OpenRouter — one key, many models, including free ones.
Keys live server-side and never reach the browser. If a provider call fails, the built-in engine takes over and the scan still completes.
What changes when you add a key
Capability
Built-in
With a key
Scanning & clustering
Full
Full
Five-signal scoring
Full
Full
Editorial re-ranking
—
Yes
Titles & descriptions
Templated
Written
Thumbnail briefs
Templated
Written
Feature questions
The detail behind the list
How does story clustering work?
Every article pulled from your feeds is normalised and compared against the others by headline and entity overlap. Reports of the same event collapse into one story, and the outlets that ran it become that story’s coverage count. This is what turns a feed of 300 articles into a list of roughly 20 distinct things that happened.
Can I trust the score, or should I read every story anyway?
Treat it as a ranking, not a verdict. The score exists to put the five or six stories worth your attention at the top of the list instead of scattered through 300 articles. Every story shows its individual signal bars, so you can see whether a high score came from real multi-outlet coverage or just a keyword match, and override it in a second.
What exactly is in a generated package?
Five title options written to different angles, a full YouTube description with the context a viewer needs, a tag list, hashtags, and five thumbnail briefs, one paired with each title, describing the shot, the words on the thumbnail and the emotional beat. From there you can draft a fact-checked script with estimated chapters and, on Creator and Studio, generate the thumbnail images. Packages are written for long-form videos, saved permanently against the story, and on Creator and Studio can be exported as CSV or Markdown.
Does the YouTube competition check cost extra?
Not from us — it is part of the Creator and Studio plans. It uses your own YouTube Data API key, which Google makes free up to 10,000 units a day. A scan checks the top stories only — roughly 1,500 units — so the free quota comfortably covers several scans per day. When it is on, each story’s score is adjusted for how crowded the topic already is on YouTube.
What counts as a breakout?
A video from a competitor channel you track that is pulling well above that channel’s normal for its age, on a topic your news feeds did not pick up. Age matters: a six-hour-old upload is compared with what that channel’s videos usually have at six hours, not with week-old totals. Breakouts are part of competitor tracking on the Studio plan.
Your next story is already breaking
See it on your own channel.
Add one channel, run one scan, and judge the ranking against what you already know about your niche.