Hook Detector

Pack 2 or 3 images of one of your thumbnails, edit or Optimize calls for YouTube Studio's Test and Compare: a zip of A, B, C (1280x720, under 2 MB) and a note of what each tests. Free. Same as POST /v1/ab.

Join the team an invite names. From then on what you spend comes from the team's pool; your own runs stay private and your own balance waits for you. Each link works once (409 invite_used) for 7 days (410 invite_expired). Needs admin. Free. Same as POST /v1/team/invites/{token}/accept.

Add channels to one of your trackers. Same as POST /v1/trackers/{tracker_id}/channels.

Owner only: add or remove an account's credits, as POST /v1/admin/accounts/{account_id}/credits. A change that would take the balance below zero is 422 credits_below_zero and nothing changes; an unknown account is 404 account_not_found. Every change is audited (admin_list_actions). Returns {account_id, credits, delta}.

Owner only: every account, newest first, as GET /v1/admin/accounts: {total, accounts: [{id, email, name, label, credits, created_at, last_seen_at, runs, hooks, charged_total, is_admin, admitted_by, keys_active}]}. Free.

Owner only: the audit of password sign-ins and credit changes, newest first, as GET /v1/admin/actions: {actions: [{id, action, actor_email, target_account_id, detail, created_at}]}. Free.

Owner only: every account's research runs, newest first, as GET /v1/admin/runs: {runs: [{run_id, account_id, email, topic, language, country, status, requested, hooks, reserved, charged, failure_kind, error, created_at, finished_at}]}. Free.

Owner only: the whole service at a glance, as GET /v1/admin/overview. Counts of accounts and people; runs (total, last_24h, last_7d, failed_24h, in_flight); hooks; credits (charged_24h, charged_7d, charged_total, balance_total); access (pending_requests, active_codes, redemptions); search (credits_left, low, accepting_runs; null when not read yet); and the running commit. Needs the admin scope and an admin account (403 admin_required otherwise). Free.

Owner only: approve an access request. Makes a one-use code, marks the request approved and emails the code. The code is in this result once, with emailed true or false; when false, send it yourself or approve again (the unused code is revoked and a new one sent). 409 request_already_decided once its code was used. Free.

Your account and remaining credits right now: account_id, credits, key_prefix and key_id of the key making this call, label, created_at, and that key's scopes, credit_limit and expires_at, and user (the person signed in with Google, or null). Same shape as GET /v1/me. A run needs at least 40 credits and reserves up to 200. For spend, credits held by in-flight runs and daily history, call usage. Free.

A channel's own outliers (scope own), or outliers for a channel like it from other channels in the shared index (scope niche, 3x and over by default). Free. Same as GET /v1/channels/{ref}/outliers.

One conversational turn, for an agent relaying a person's words. It either asks ONE clarifying question (action "clarify"), answers about delivered hooks or the tool (action "answer", run null, no credits), or starts a research run (action "research", with the started run under "run"), exactly like POST /v1/chat. Every response has suggestions: 0 to 4 follow-ups, [] for research.

A deck size typed into the message ("..., 15 hooks") and a recency phrase ("this
month", "last week") set the run's count and posted_within_days; the count argument
sets the deck size when the message states none. Asked to make one of
the conversation's hooks yours for a niche ("make hook 2 mine for dentists"), the turn
writes lines from that hook's structure (1 credit, like remix_hook) and answers them
labelled, the full result under "remix".

language and country select the search locale: omitted or null keeps the current
conversation setting; a value sets it for this and later turns; an empty string
clears it to any language / any country. The picker wins over the message's locale;
replies stay in the language the person writes in. Invalid locale: 422 invalid_request.

message is 1 to 4000 characters. Pass conversation_id from an earlier turn to keep
the context; leave it out to start a conversation. Cost: a turn itself is free but is
a model call, so turns are limited per account per hour (429 rate_limited); a turn
that starts a run reserves credits like find_hooks. Next step: on "research", call
get_run with run.run_id and wait_seconds=50. Errors: 503 model_unavailable when the
model is down (nothing charged, try again), 402 insufficient_credits. For direct
research without the question step, call find_hooks instead. Needs the write
permission, and research for a turn that starts a run (403 insufficient_scope, nothing
reserved).

The talking-head cleaner (15 credits), like 1of10's AutoCut: silences tightened, retakes, false starts, stutters and fillers cut with a reason on every cut, other microphones or cameras synced to the first, as Premiere XML, FCPXML and a CMX 3600 EDL. Takes 1 to 4 file_id values staged with POST /v1/clean/files (a chat cannot send the file itself). Runs as a job; get_call reads it. Same as POST /v1/clean.

Undo keep_hook: the hook goes back to having no verdict, so it leaves list_keeps and its export row carries none. Returns {"hook_id", "verdict": null}. Clearing a hook with no decision is the same success, so a retry is safe. Same as DELETE /v1/hooks/{hook_id}/decision. Free. Errors: 404 hook_not_found, 422 for an id that is not a UUID.

Undo keep_find: the video goes back to having no verdict, on every find of it, and leaves list_kept_finds. Returns {"find_id", "verdict": null}. Clearing a find with no decision is the same success, so a retry is safe. Same as DELETE /v1/finds/{find_id}/decision. Free.

Copy a public or shared tracker into a private one of yours. Same as POST /v1/trackers/{tracker_id}/clone.

End your poll now: no more votes, the votes so far kept with its results. Free. Same as POST /v1/polls/{poll_id}/close.

What a subject's audience asks and struggles with: the top comments of its outliers (videos that beat their own channel; or your video_ids, or a channel's best uploads), grouped into questions, pain points and requests. clusters: label, kind (question, pain_point, request, other), count (comments in the group, counted in code, never by the model), likes, videos, and quotes: two real comments found word for word, each with its link (url opens the comment). videos: what was read, with views, multiple (views over the channel's usual), comments_read and comments_off. basis says what the counts are from. Costs 3 credits, refunded when the read fails; a request naming nothing or two things is 422 and costs nothing. Takes about 60 to 100 seconds (measured 2026-10-26). Same as POST /v1/comments/insights. Read it back with get_call.

Owner only: make an access code to hand out. max_uses 1 to 100000 (default 1), expires_in_days 1 to 365 (optional), note your own. email binds it to one person: then only Google sign-in with that verified email redeems it, never the API or MCP; leave it out for a code that works on every door. The code is in this result only. Free.

Create an account and get an API key with free credits. Needs a beta access code (access_code, HD-XXXX-XXXX; case and dashes do not matter): without one the error is 403 access_code_required, and a code that does not work is 403 invalid_access_code. Ask for a code with request_access, or at hookdetector.com/access. No key needed for this call. label is an optional note up to 120 characters.

Keep the api_key it returns: it is the only copy. Send it as the header
'Authorization: Bearer hd_...' or pass it as api_key on every other tool. Signups,
and wrong codes, are limited per address per hour. Next step: find_hooks.

An agent that runs a Video Review on each new long upload of a tracker's channels, inside a monthly credit budget. Same as POST /v1/agents.

Save a search checked daily or weekly; a new video at your line (default 3x its channel) is a hit, emailed, with a Monday digest. 1 credit a check. Same as POST /v1/alerts.

Make a named folder on one tab to file hooks or finds in. The same name again on that tab (case and spaces aside) returns the folder already there with created false, so a retry never makes two. At most 200 folders an account (409 folder_limit_reached). Returns the folder: folder_id, kind, name, item_count, cover, shared, share_url, created. Same as POST /v1/folders. Free. Next: save_to_folder.

Create another API key on your account, for example one per agent or machine, so you can revoke one without touching the others. name is up to 60 characters.

Give the key only what it needs. scopes: any of "read" (read runs, hooks, keeps,
usage), "write" (keep, reject, undo, chat), "research" (start runs, which spend
credits), "admin" (manage keys, delete the account); all four when left out. An agent
that finds hooks needs ["read", "write", "research"]. credit_limit: the most credits
runs started with this key may spend over its life, 1 to 100000 (a run then reserves
at most what is left). expires_in_days: 1 to 365; the key then stops working (401
key_expired).

The new key is in this result once and never again: store it now. Needs admin. An
account holds at most 10 active keys (409 beyond) and may create 20 per hour by
default (429 beyond). Free.
Next step: use the returned api_key; revoke old ones with revoke_key.

Put 2 to 4 packages to Hook Detector's users, who pick the one they would click, blind. Closes at votes_wanted or after 7 days. 2 credits, given back when a picture cannot be stored. Results with get_poll. Same as POST /v1/polls.

Create a team this account owns, funding its pool from your balance with credits (402 when you hold less). Members' spending comes from the pool; you keep spending your own balance. 409 already_in_team. Needs admin. Free. Same as POST /v1/team.

Make a tracker of up to 50 channels: hourly reads of their newest uploads, alerts when one reaches the multiple (default 3x its channel) or views per hour, in the app and by email. 1 credit a tracked channel a day. Same as POST /v1/trackers.

Post every new tracker alert and saved-search hit to your https URL, signed with the secret this returns once (X-HD-Signature). Same as POST /v1/webhooks.

Your daily idea sets (turn them on per saved search or tracker with daily_ideas), each idea with the real finds behind it, none repeated within a week. Same as GET /v1/ideas/daily.

Erase your account and everything in it, for good: every API key, run, hook, keep or reject decision, conversation and message. Unspent credits go with it. It cannot be undone.

confirm must be exactly "delete my account", or nothing happens (422
confirmation_required). Refused with 409 run_in_flight while a run is queued or
running: wait for it with get_run first. Returns {"deleted": true, "account_id",
"erased": {counts per kind}, "message"}. Every key of the account stops working at
once; create_account starts a new one. Same as DELETE /v1/account. Free.

Delete one of your agents. Same as DELETE /v1/agents/{agent_id}.

Delete a saved search. Same as DELETE /v1/alerts/{alert_id}.

Delete a folder, its items and its share link at once (the link stops working). The hooks and finds in it, and their keeps, stay. Returns {"folder_id", "deleted": true}. Same as DELETE /v1/folders/{folder_id}. Free. Errors: 404 folder_not_found.

Delete your poll, its votes and its pictures. Free. Same as DELETE /v1/polls/{poll_id}.

Delete one of your presets. Same as DELETE /v1/presets/{preset_id}. Free. Errors: 404 preset_not_found.

Delete one of your trackers. Same as DELETE /v1/trackers/{tracker_id}.

Delete one of your webhooks. Same as DELETE /v1/webhooks/{webhook_id}.

Set the note on one item of a folder. Returns the item. Same as PATCH /v1/folders/{folder_id}/items/{item_id}. Free. Errors: 404 item_not_found.

Edit one thumbnail (an image of your thumbnails call, or a picture you send): op erase, edit, face_swap, text, text_variations, upscale, fix, crop or color. crop and color are free; upscale 12; the rest 4 (a version each for text_variations), charged only for what is delivered. Answers at once; read it with get_thumbnails. Same as POST /v1/thumbnails/edit.

Official TikTok or Instagram embed HTML for a hook, so the clip plays inside your own page. kind is "embed", or "fallback" when the creator disabled embedding or the clip is a photo post found before 2026-09-26 (then show thumbnail, which falls back to the hook's still_url, and the transcript). For a plain vertical iframe use the hook's player_url instead. Free.

A finished run's hooks as a file a creator can open: format "csv" (default; one row per hook, opens in any spreadsheet, formula-like cells defused with a leading quote), "json" (the full hook objects) or "md" (Markdown notes, one section per hook).

Returns {"filename", "content_type", "format", "content"}, where content is the whole
file as text: write it to filename. The same bytes as GET
/v1/runs/{run_id}/export?format=... . Free.
Errors: 404 run_not_found, 409 run_not_finished while the run is queued or running
(call get_run with wait_seconds=50 first), 422 invalid_request for another format.

Start hook research on a topic across TikTok, Instagram and YouTube Shorts (Shorts only, never long-form YouTube; platform "youtube"). platforms (since 2026-10-10, any of "tiktok", "instagram", "youtube"; all three when left out) searches and delivers only those: ["instagram"] is Instagram reels only.

What it does: searches both platforms, reads what each clip says and shows, and
returns ranked hooks. Each hook has its verbatim opening line, most quotable line,
main idea, why it travelled, topic, on-screen text, full transcript, a watch link and
a vertical player_url (9:16 iframe).

Talking heads only (since 2026-09-29): `hooks` holds only clips where a person on
camera is talking (talking head, podcast, interview). A clip where nobody talks is
dropped; Bonus was removed on 2026-10-08 and `bonus` is always []. Every hook carries
format (talking_head, podcast, interview, stage; null on older hooks) and section
(always "main"). A run that finds fewer talking heads than count says so in outcome;
it never fills hooks with clips that do not talk.

Where it comes from (since 2026-09-30): every hook has creator_country (ISO alpha-2
of the creator's TikTok account; always null on Instagram, which states none), place
(the place the creator tagged, or null) and place_country (that place's country when
the platform states it). Never guessed.

Banner (since 2026-09-30): every hook has banner, the title-style text the creator
placed on the video to hook the viewer, verbatim (at most 200 characters), or null
when it has none; subtitles are never a banner. onscreen_text keeps all text read.

Match (since 2026-09-30, runs with a language or country): every hook has match,
"exact" when the clip is about the subject itself or "close" when it is about a
neighbouring subject with the same intent (a close match, delivered after every exact
match; label it as one); null on runs with no language or country and on older hooks.

Analysis (since 2026-10-02): every hook carries hook_type (curiosity_gap,
contrarian_claim, specific_number, identity_callout, stakes_threat, promise_payoff,
pattern_interrupt, story_open, question, direct_command, other with hook_type_other),
mechanism (why the opening stops the scroll, quoting the clip; why_it_travelled holds
the same text), visual_hook, audience, template and steal_it; null on older hooks.

Virality v2 (since 2026-10-01): the deck is ranked by virality (0 to 1, since
2026-10-02 on one fixed scale, the same clip scoring the same in every run), built from outlier (views over the creator's usual views per video,
creator_median_views, with outlier_basis saying how it was measured), freshness
(posted_at, age_days, views_per_day), travel (shares and saves per 1,000 views),
own_sound and sound_reuse, and a paid penalty; virality_why names the strongest
signal in one line. Every hook also carries duration_s and hashtags. Null on older
hooks. posted_within_days (7, 30, 90 or 365) keeps the search to recent clips (a clip
under 7 days old passes the floor at 10,000 views a day). seed_hook_ids (up to 10 of
your hooks, for example kept ones) means "find more like these": their lines, topics,
creators and languages steer the search, and a seed is never delivered again. A done
run carries patterns: up to 3 hook structures winning in the deck (name, template,
why, hook_ids, count), computed after delivery; null until then. remix_hook writes
lines from one hook's structure for your niche (1 credit).

Arguments: topic is 3 to 500 characters, count 1 to 30 (default 10). Instructions
inside the topic are fine: only the subject read out of it is searched. reuse=true
(default) starts from clips you already paid for on the same topic, so a rerun is
close to free and often finishes in seconds. idempotency_key: any string up to 255
characters; the same key within 24 hours returns the first run instead of starting
and paying for a second one, so always pass one and reuse it when you retry.
wait_seconds 0 to 50: 0 returns the run_id at once; above 0 waits for the run and
returns the run object, as get_run does.

Any language, dialect or country: language is optional free text up to 60 characters
naming the language or dialect every clip must be in ("Moroccan Darija", "ar-MA",
"Egyptian Arabic", "Brazilian Portuguese"); country is an optional ISO 3166-1 alpha-2
code for where the creators are (MA, EG, BR). Saying it inside topic works too; these
fields win when both are given. A country alone does not restrict the language. Each
hook reports the language it was judged to be in.

A region that is not a country: send its country's code and name the regional variety
in language (Quebec: country "CA", language "Quebec French"; Flanders: "BE" and
"Flemish"; Catalonia: "ES" and "Catalan"). The country places the TikTok search there
and the language judge does the regional filtering; Instagram reports no country.
language may name a mixed, code-switched variety ("Hinglish", "Taglish", "Moroccan
Darija with French") or two joined by "or" ("Tagalog or Taglish"); it reaches the
judges exactly as written, and how well they honour such a value is not measured yet.

Cost: reserves up to 200 credits up front (less if your balance is smaller, down to
40) and charges only what it used; the rest is refunded. A failed run costs nothing,
and so does a run that finds no hooks, within a per-account allowance (llms.txt has
the numbers; its outcome says which applied).

Timing and next step: a fresh run takes about 2 to 3 minutes, up to about 5 when the
language is a dialect. Call get_run with wait_seconds=50 repeatedly until status is
"done" or "failed", which is usually 3 or 4 calls (up to 6 on a dialect request). Watch progress.stage and progress.message meanwhile.

Needs a key with the research permission (403 insufficient_scope otherwise). A key
with a credit_limit reserves at most what is left of it; under the minimum it is 403
key_credit_limit_reached and nothing is reserved.

Find long-form hooks: how the YouTube videos that beat their own channel open, on a topic. Long-form YouTube only, never Shorts, TikTok or Instagram (for those: find_hooks).

What it does: searches YouTube for long-form videos on the topic, keeps only the
outliers (a video whose views are at least min_outlier times the median views of its
own channel's recent uploads; 2 by default) posted in 2023 or later (nothing older is
ever delivered), reads the first intro_seconds (60 by default) of each one's
transcript, and says why that opening holds a viewer.

What comes back: the run's `finds`, ranked, strongest outlier first. Each has title,
channel, watch_url, player_url (an iframe src), thumbnail_url, views,
channel_median_views, outlier (28.2 means 28 times the channel's usual), outlier_score
(0 to 100 on one fixed scale: nothing else a run found moves it, so finds from
different runs rank together), outlier_tier, channel_size, likes_per_1k, posted_at,
duration_s, and the opening: intro (the first minute as it was said: lines of n, t in
seconds, text) and intro_text, always whole; and inside it the hook (verbatim: the lines
the analysis marks as the hook, ending on a sentence end, at most 25 seconds and 60
words, with hook_words, hook_start_s and hook_end_s, a sponsor read or greeting at the
front left out; hook_seconds is hook_end_s). auto_captions says the opening has almost
no punctuation. about_subject is yes or partly: a video the model judges not to be
about the subject is dropped. The analysis: hook_type (the same list as find_hooks),
mechanism (why it holds, quoting the opening word for word), promise, open_loop,
title_link (how the first lines pay off the title), beats (the opening in parts: from,
to, beat, does),
opens_with (cold_open, greeting, teaser, question, sponsor), format (the kind of
video), angle, template (the hook as a fill-in structure), steal_it and audience. When
the topic asks for a kind of opening ("question hooks", "storytime"), style_match says
whether each find is that kind and the matches come first. analysed is false
when the model could not analyse an opening: the opening is still real, its analysis
fields are null. The run's report.patterns lists the opening types at least two finds
share; report.shape says how the openings are built, counted from the finds
(hook_seconds, how long the hook runs, and hook_words as medians, beats with how many
openings use each and the second it usually starts_at, and the sequence of beats most
of them share); and
report.openers holds up to `openers` (3 by default, 0 for none) openings WRITTEN for
your topic from those structures (hook, then, hook_type, based_on). report.openers_label
is always "Written by Hook Detector from the structure of these real openings": show
it with them, never present one as a real video's opening. report.landscape is the
subject at a glance, counted from the videos the run held against their own channel
(videos, channels, outliers and their share, breakouts, small_channel_outliers,
recent_outliers). The run's hooks and bonus are always empty.

A link instead of a subject: when topic is a channel's YouTube address
(https://www.youtube.com/@name, or just @name) the run returns that channel's OWN
outliers, its recent long-form uploads that beat its usual (one provider call, no
search); when it is a long-form video's address the run returns that one video,
whatever its multiple (requested is 1). options.link says "channel" or "video". No
openings are written for a link (use remix_find on a find to write for your niche).
A Short's address is refused with 422.

Arguments: topic 3 to 500 characters; count 1 to 30 (default 8); language and country
optional; posted_within_days 30, 90, 365 or 730 to narrow the 2023 floor further;
channel_size "small", "medium" or "large" to keep only channels of that size (by what
their uploads usually get), so a small creator sees breakouts from channels their own
size; reuse=true (default) starts from the videos your last long or packaging run on
this topic bought within a week, and a video you already had read is delivered from
that read (analysis_from_earlier_read) at no model or provider cost. seen_before says
an earlier run of yours already found the video. idempotency_key: always pass one and
reuse it on a retry. wait_seconds 0 to 50: 0 returns the run_id at once; above 0 waits
and returns the run. Starts are limited per account per hour (429 rate_limited).

Cost: reserves up to 90 credits for 20 videos or fewer and 5 more for each video above
that (140 at 30; less on a smaller balance, down to 25) and charges
only the provider calls it made: the searches, one call per channel measured, one per
transcript read. A failed run costs nothing, and so does a run that
finds nothing, inside the same allowance a hook run has (the outcome says so).

Timing and next step: how long a run takes has not been measured yet, so never assume
a time. Call get_run with wait_seconds=50 until status is done or failed;
progress.items holds the finds written so far as cards
and progress.scan the videos it is looking at while it runs. Then keep_find, export_run. Same as POST /v1/longform. Needs the research
permission (403 insufficient_scope otherwise).

Find packaging: the titles and thumbnails that earned the click on a topic, from long-form YouTube videos that beat their own channel.

What it does: runs the same outlier search as find_long_hooks (long-form YouTube,
2023 or later, views at least min_outlier times the channel's usual), then looks at
each video's thumbnail beside its title and says what the pair is doing.

What comes back: the run's `finds`, ranked. Each is a real package, as YouTube shows
it: title (verbatim) and thumbnail_url (the size YouTube really served, the picture
the analysis looked at; thumbnail_checked says so), channel, watch_url, views,
channel_median_views, outlier, outlier_score (0 to 100 on one fixed scale, so finds
from different runs rank together), outlier_tier, channel_size and posted_at, plus the analysis: title_device (curiosity_gap, contrarian_claim,
specific_number, how_to, listicle, challenge, story, question, warning, comparison,
authority, timeliness, identity_callout, other), title_template (the title as a
fill-in structure), thumbnail_text (the words printed on the thumbnail, read by a vision
model; null when none), thumbnail_text_role (repeats_title, adds_to_title,
contrasts_title, no_text; counted from title_overlap, the share of the thumbnail's words
that are also in the title, where that can be), thumbnail_subject, thumbnail_faces,
thumbnail_emotion,
thumbnail_colors, thumbnail_composition, thumbnail_devices, angle, gap (what the picture shows that the title does not say, and the
question that leaves), promise, steal_it and audience, visible_action (the single thing
happening in the picture), title_carries and picture_adds (what only the title says,
what only the picture adds), text_box, and thumb_metrics (measured in code from the
pixels: palette, brightness, contrast, saturation, busyness, the biggest words' height
at 210 px wide and whether the length corner is clear), plus cut_on_phone (the title is
longer than 60 characters, where a phone roughly cuts it; approximate) and on_subject
(yes or partly: whether the look judged the package to be about your topic; a package
judged not to be is dropped and the next one takes its slot; null on a link run). analysed
is false when a package could not be looked at (its look is asked twice, and the next
candidate takes the slot if it fails twice); it is still a real package.

The run's report then holds title_patterns and thumbnail_patterns (what at least two
of the packages share, each naming their video_ids) and ideas: up to `ideas` (6 by
default, 0 for none) packages WRITTEN for your topic from those patterns, each a title
a thumbnail concept and thumbnail_text (the words to print on it), naming the real
packages it is based_on. report.ideas_label is always "Written by Hook Detector from
the patterns in these real packages": show it with them, never present an idea as a
real video's title; an idea over 70 characters, with more than 5 words for its
thumbnail or repeating a real title is dropped. report.numbers counts the packages:
title_chars and title_words
(medians), titles_with_number, titles_with_question, titles_cut_on_phone (with
phone_title_chars, the approximate length a phone cuts a title at), thumbnails_with_text
and thumbnail_words (over the analysed ones), and the title_devices, thumbnail_devices and
emotions that repeat (name, count); age_cohorts repeats the counts for packages posted in
the last split_days days (recent) and for older ones, with the undated apart.
report.landscape is the subject at a glance, as on find_long_hooks.

Arguments: topic 3 to 500 characters, or a channel's or a long-form video's YouTube
address exactly as on find_long_hooks (a channel's own outliers, or that one video; no
ideas are written for a link, use remix_find); count 1 to 30 (default 12); language,
country, min_outlier, posted_within_days, channel_size and reuse as on
find_long_hooks; idempotency_key and wait_seconds as on find_hooks; content_type
"short" finds the packages of YouTube Shorts instead of long-form videos ("long", the
default), each Short measured against its own channel's Shorts. Every find carries
multiple (views over the channel's median, the number 1of10 and vidIQ show),
multiple_band (10x, 5x, 2x, under 2x) and content_type.

Cost: reserves up to 70 credits for 24 packages or fewer and 3 more for each package
above that (88 at 30; down to 25) and charges only the provider calls it
made: the searches, one call per channel measured, and one for each video whose date
had to be read exactly. Looking at a thumbnail costs no credit. After a find_long_hooks run on the same topic it is close
to free. A failed run costs nothing, and so does a run that finds nothing, inside the
allowance.

Timing and next step: how long a run takes has not been measured yet, so never assume
a time. Call get_run with wait_seconds=50 until status is done or failed;
progress.items holds the packages looked at so far as cards and progress.scan the videos
it is looking at while it runs. Same as POST /v1/packaging. Needs the research
permission.

The videos in the shared index nearest one of your finds (find_id from a Packaging or Long form run), nearest first, never the find's own video. Each has distance (0 is the same; measures says how it is computed), its numbers and its multiple over its channel's median. A find not indexed yet is matched by its own words (matched_from). Free. Same as GET /v1/finds/{find_id}/similar. Errors: 404 find_not_found.

Who sponsors the channels on a subject: in the descriptions of its outliers, sponsor lines, promo codes and offer links found in code, plus Scrape Creators' sponsor read of videos YouTube marks as paid promotion, each named by one model read and kept only when the brand's name is in its own line. sponsors: brand, kind (sponsor, affiliate, other), channel_count and video_count (counted in code), channels, and videos with the evidence line as written, the code and the link. Costs 1 credit, refunded when the read fails. Same as POST /v1/sponsors. Read it back with get_call.

One title format's videos, strongest first. Free. Same as GET /v1/formats/{format_id}.

One agent and its reviews (done, skipped or failed, and why). Same as GET /v1/agents/{agent_id}.

One saved search and its hits. Same as GET /v1/alerts/{alert_id}.

One call of a priced tool (titles and the tools after it): tool, credits, charged, status (pending, done, failed), request and result. Same as GET /v1/calls/{call_id}. Free. Errors: 404 call_not_found.

A channel page: subscribers and totals, every recent long upload scored against the channel itself (outliers at 2x its median and over), and its momentum. Free. Same as GET /v1/channels/{ref}.

One chat conversation: its newest messages in order (role, content, run_id, created_at), a page of limit, with earlier_cursor for the older ones (null when the page reaches the first message), and the runs those messages hold, with their hooks, plus nullable language and country search picker settings. Same shape as GET /v1/conversations/{conversation_id}. Free. Errors: 404 conversation_not_found, 422 for an id that is not a UUID or a cursor this API did not issue.

One result of a long or packaging run with every field: the video, its numbers and the opening or the package analysis. find_id comes from a run's finds (get_run) or from list_kept_finds. Same shape as GET /v1/finds/{find_id}. Free. Errors: 404 find_not_found, 422 for an id that is not a UUID.

One of your folders and its items, newest filed first, limit 1 to 100 a page (page with next_cursor). Each item has item_id, note, thumbnail_url, title and the full hook or find object. Same as GET /v1/folders/{folder_id}. Free. Errors: 404 folder_not_found.

One hook with every field: its opening line, transcript, watch_url and the vertical player_url (null only for an unusable id or a photo post found before 2026-09-26; runs deliver single videos only). hook_id comes from get_run. Free.

One background job of this account. Same as GET /v1/jobs/{job_id}. Errors: 404 job_not_found for another account's job or an unknown id.

An Optimize call: the original's score and every new package so far. Same as GET /v1/optimize/{call_id}. Free.

One poll: yours with votes, shares, 95% intervals, the leader once the votes separate, the slots and the reasons; or one you voted on with its shares. Free. Same as GET /v1/polls/{poll_id}.

One remix you paid for (from remix_hook, remix_find or a chat turn), as its answer held it. Free. 404 remix_not_found for one that is not yours. Same as GET /v1/remixes/{remix_id}.

One research page: every claim with the first run's and the second run's numbers (each run a sample of different channels), n per run and per cell, shown_a and shown_b (over the sample bar), reproduced (true, false, or null for too few) and direction, plus measures naming what each number is computed from. 404 page_not_found for an unknown slug, 422 for a malformed one. No key needed; limited per address. Free. Same as GET /v1/findings/{slug}.

A research run: its status, progress, charge and every hook it produced.

wait_seconds 0 to 50: wait up to that long for the run to finish, returning the
moment it is done or failed. Use wait_seconds=50 and call again while status is
"queued" or "running"; a fresh run needs about 3 or 4 such calls. progress has
stage, message and updated_at, plus counts once the research reports them, preview
(hooks written so far) while a running run holds one, and feed (the live research
wall: up to 24 clips the run is working on, newest first, each key, platform, creator,
views, state found|reading|talking|passed, thumb_url, a JPEG any <img> can load
with no key, and line, the banner or opening words once the judges passed the clip)
while it shows one, and on a Long form or Packaging run scan (the videos it is looking
at: up to 60 tiles {v: YouTube video id, s: found|on_topic|off_topic|measured|beat|
reading|ready|passed, x: multiple of the channel's usual or null}, oldest first, and
lanes with found, on_topic, measured, beat, reading, ready; draw a tile from
https://i.ytimg.com/vi/{v}/mqdefault.jpg; counts.measured and counts.beat are the
numbers report.landscape ends on). Pass since with the last
progress.updated_at to return on change or completion. It must be an ISO timestamp
with a timezone (422 invalid_request otherwise). `hooks` is the deck (a person
talking); `bonus` is always [] (removed 2026-10-08). Every hook has format and
section (always "main"), and
creator_country (TikTok only), place and place_country (null when unknown), banner
(the title placed on the video, null when none) and match ("exact" or "close", a
close match being a neighbouring subject delivered after the exact ones; null on runs
with no language or country and on older hooks). Since 2026-10-04 the run carries
understood (what the request was read to ask: subject, language, country, core,
audience, neighbours, styles, style_other, wants; null until read) and, on a run that
asked for a kind of opening ("controversial hooks", "storytime"), every hook carries
style_match (true when it opens that way; null otherwise). Since 2026-10-01 every hook carries
the virality v2 fields: virality (0 to 1 on one fixed scale since 2026-10-02),
virality_why, outlier, outlier_basis, creator_median_views, posted_at, age_days,
views_per_day, duration_s, paid, sound_reuse, own_sound, hashtags (null on older
hooks), and since 2026-10-02 the analysis: hook_type, hook_type_other, mechanism,
visual_hook, audience, template, steal_it; the run echoes posted_within_days and
seed_hook_ids, and once done carries
patterns: up to 3 hook structures winning in this deck, each name, template, why,
hook_ids and count, grouped by hook_type and computed before the run is done, in the
deck's language (null on older runs and when nothing is shared). Hooks include
transcript_kind:
speech, music, none, other, or null when unknown; and heard: false when our speech
service could not hear the clip right now (no spoken words shown, transcript null; the
done message then counts them), true otherwise. conversation_id names the chat conversation the run
belongs to (null outside one). A done run with fewer hooks than asked for, or none,
has outcome: why in one plain paragraph, what to try next, and whether it was free
(stats.rejections holds the counts); a full run's outcome is null, or one sentence
when some hooks are under the view floor because the country filter set clips aside.
Free: reading a run costs no credits.

A shared folder as anyone with its link sees it: name, description, kind, item_count and items (public fields and the owner's note), newest first, paged. No key needed; limited per address (429). A link never made or turned off is 404 shared_folder_not_found. Same as GET /v1/shared/folders/{token}. Free.

The skeleton of a long find's whole video, heard by Scribe v2: sections, re-hooks, open loops, payoffs, sponsor and call-to-action spans, the outro, the timed lines. Builds it once for 5 credits as a paid call (status pending; read it with get_call); after that answers the stored one free. Same as POST and GET /v1/finds/{find_id}/skeleton.

Your team, or team null: its name, pool (credits), seats, each member's name and role. The owner also sees every member's email, monthly cap and spend, open invites (never their links) and the newest 50 charges to the pool (who, what kind, credits, when; never what it was about). your_credits is your own balance, untouched while you are a member. Free. Same as GET /v1/team.

A thumbnails call: status, concepts and every image so far (url signed for 7 days, width, height, words, words_checked, cost_usd). Same as GET /v1/thumbnails/{call_id}. Free.

One tracker and its channels. Same as GET /v1/trackers/{tracker_id}.

Invite someone: returns link (and its token), a single-use page valid 7 days, shown here only, and emailed to that address (emailed true; when false, give the link to the person yourself). Someone signed in with Google must hold that email to accept. Owner only. Needs admin. Free. Same as POST /v1/team/invites.

Keep or reject a find (a long-form hook or a package): verdict is "keep" (default) or "reject", and the last verdict wins. The verdict is the video's on that tab: every find of the same video you have there carries it, so a later run that finds the video again shows it already kept. Kept videos come back from list_kept_finds, across all runs. Returns {"find_id", "verdict"}. Same as POST /v1/finds/{find_id}/decision. Free. Errors: 404 find_not_found.

Keep or reject a hook: verdict is "keep" (default) or "reject", and the last verdict wins. A reject may say why: reason is off_subject, weak_opening, wrong_language, low_quality, already_have or other, and note (up to 280 characters) your own words. Kept hooks come back from list_keeps, across all runs. Free.

Owner only: every access code, newest first, with code_id, code_prefix, email, note, source, max_uses, uses, expires_at, revoked_at, created_at and usable. Never the code itself. Free.

Owner only: every access request, newest first, optionally only one status (pending, approved, rejected). Each has request_id, email, note, status, code_id, code_prefix, created_at and decided_at. Never a code. Needs the admin scope and an admin account (403 admin_required otherwise). Free.

Your agents with their budgets and this month's spend. Free. Same as GET /v1/agents.

Your saved searches and their newest hits. Free. Same as GET /v1/alerts.

Your calls of priced tools, newest first; tool ("titles", ...) narrows. Same as GET /v1/calls. Free.

Your chat conversations, most recently active first, limit 1 to 100 (default 30) per page: conversation_id, title, created_at, updated_at, language, country and messages (the count). Nullable language/country are the saved search picker settings. Returns {"conversations": [...], "next_cursor"}; pass next_cursor back as cursor for more. Same shape as GET /v1/conversations. Next step: get_conversation. Free.

The index: every video your long and packaging runs found, across all runs, one entry a video on each tab (its newest read, with the keep or reject made on the video). Each is a full find object: the title and thumbnail_url as YouTube shows them, views, channel_median_views, outlier (views over the channel's usual) and outlier_score (0 to 100 on one fixed scale, so entries from different runs rank together), plus the analysis its run wrote. q (at most 120 characters) looks in the title, the channel, the hook as it was said, and what the thumbnail prints and shows, so a package can be found by its thumbnail ("red arrow", "before and after"). Returns {"finds", "count", "total" (every match, on any page), "next_cursor"}; pass next_cursor as cursor for the next page. Use it to search what you already paid for before starting a new run. Same as GET /v1/finds. Free. Errors: 422 for a kind, sort, tier, min_score, device or q that is not allowed. The bounds min_multiple to language (T3-FL) narrow the index on the server, as on GET /v1/finds; an entry that does not carry a bounded field is left out.

Your folders, the most recently changed first, each with item_count, up to 4 cover thumbnails and its share link when shared. With hook_id or find_id, each folder also has contains: the item id when it holds that video (any run's copy), else null. Returns {"folders": [...], "count"}. Same as GET /v1/folders. Free.

Title formats of the last 90 days with their median multiple, share over 1.5x, adoption and examples, ordered by the Wilson lower bound of that share (computed_from). Formats with at least 8 measured videos from 3 channels (each shows measured beside videos); include_small lists down to 3 from 2. Free. Same as GET /v1/formats.

This account's background jobs, newest first (tracker refreshes, alerts, reviews, echo): status, attempts, credits, result or error. Free. Same as GET /v1/jobs.

The hooks you kept with keep_hook, newest decision first, across all runs or within one run_id, limit 1 to 100 (default 100) per page. Returns {"kept": [...], "count": n on this page, "next_cursor"} with full hook objects; pass next_cursor back as cursor for more. Same shape as GET /v1/keeps. Free. Errors: 422 for a bad run_id or cursor.

The videos you kept with keep_find (long-form hooks and packages), newest decision first: one entry a video on each tab across all runs, or the kept finds of one run_id, limit 1 to 100 (default 100) per page. Returns {"kept": [...], "count": n on this page, "next_cursor"} with full find objects. Same shape as GET /v1/finds/keeps. Free. Errors: 422 for a bad kind, run_id or cursor.

Your API keys and what each may do. keys: key_id, name, prefix, created_at, last_used_at and current (true for the key making this call). access, per key_id: scopes, credit_limit, credits_used, expires_at and expired. scopes: the calling key's. The original signup key has key_id "original". The keys themselves are never shown again. Needs admin. Same shape as GET /v1/keys. Free.

The niche explorer: every niche reported, with its headline numbers. Free. Same as GET /v1/niches.

Your package votes, newest first, with their results so far. Free. Same as GET /v1/polls.

Your saved filter presets, the newest change first; tab ("long", "packaging", "library") narrows. Same as GET /v1/presets. Free.

The remixes you paid for from one hook (hook_id) or one find (find_id), newest first, each as its answer held it, with remix_id and created_at. Returns {"remixes": [...]}. Free. 404 hook_not_found or find_not_found for one that is not yours. Same as GET /v1/hooks/{hook_id}/remixes and GET /v1/finds/{find_id}/remixes.

The research findings counted from Hook Detector's shared index of public YouTube data: openings (which openings sit before a steeper or flatter first minute of YouTube's "most replayed" heatmap, replay intensity, not retention), title-devices (which title devices go with higher multiples, by niche) and title-thumbnail-overlap (title and thumbnail word overlap against the multiple). Each page with n per run and how many claims reproduced on a second sample of other channels, did not, or had too few videos. No key needed; limited per address (429). Free. Same as GET /v1/findings.

Your research runs, newest first, without their results, limit 1 to 100 (default 20) per page. Each run says its kind: "short" (find_hooks), "long" (find_long_hooks) or "packaging" (find_packaging); pass kind to list only one. Returns {"runs": [...], "next_cursor"}: pass next_cursor back as cursor for the next page; it is null on the last. Same shape as GET /v1/runs. Next step: open one with get_run, or download it with export_run. Free. Errors: 422 invalid_cursor for a cursor this API did not issue, 422 for a kind that is not one of the three.

The hook strategy library: every kind of long-form hook the shared index holds at least 3 openings of, with its plain name, count, the median multiple of those videos over their channels' usual views, the median hook length in seconds, the template most share, and up to 3 real examples (title, hook as said, video_id, channel, multiple). Counted from the index, never by a model; public data only. Free. Same as GET /v1/strategies.

Your trackers, or every public one. Free. Same as GET /v1/trackers.

Rising words and phrases in the shared index's titles, this window against the one before, with counts and growth. Free. Same as GET /v1/trends.

Your webhooks with their events and state (never the secret). Same as GET /v1/webhooks.

Real title and thumbnail changes on other channels: both versions (the pictures as URLs), views per hour before and 24 to 72 hours after, the lift and when the spike came. Free. Same as GET /v1/winners.

Make 2 to 12 thumbnails (default 4): 3 different concepts first, then images (Nano Banana 2.1, 1K or 4K), every printed word read back and checked letter by letter, a face only from your photos or your channel's own thumbnails. Answers at once with call_id and status pending; read it with get_thumbnails until done. 4 credits a delivered 1K image, 12 a 4K one, charged only for what is delivered. Same as POST /v1/thumbnails.

Move credits between your balance and the team's pool; 402 when the side giving holds less, and nothing moves. Owner only. Needs admin. Free. Same as POST /v1/team/credits.

A poll of another Hook Detector user waiting for your vote (not one you passed in skip): its options in an order of your own, no counts; poll null when none is waiting. Free. Same as GET /v1/polls/next.

A niche report counted from the shared index: videos, channels, median views, the share at 10x and over, the 75th percentile multiple, top outliers and channels, by month. Free. Same as GET /v1/niches/{slug}.

New packages (4, 8 or 12) for your published video: the original scored first against the real outliers on its subject, then each new package (title, thumbnail with every word checked, what it tests) scored the same way, best first, with vs_original. 10 credits a delivered package. Answers at once; read it with get_optimize. Same as POST /v1/optimize.

Your package in a mock YouTube feed among a run's winners: view home, search, sidebar, phone (marks where a phone cuts the title) or tv; theme dark or light; look normal, grey or blur. Returns png_base64 and mine_at. Free. Same as POST /v1/packaging/preview.

Outliers at random from the shared index (5x their channel's usual and over by default), a different set each call. Free. Same as GET /v1/index/random.

Read a YouTube Studio audience retention screenshot (base64 PNG or JPEG) into 100 points and the 21 marks it was read from (1 credit). Not the chart is 422 not_a_retention_chart, free. Same as POST /v1/review/graph.

New thumbnails for your video with a YouTube video's own thumbnail as the layout reference (2 to 4 images, every printed word checked); priced as make_thumbnails. Same as POST /v1/thumbnails/recreate; read it with get_thumbnails.

Owner only: reject a pending access request. Nothing is emailed. An approved or rejected request is 409 request_already_decided. Free.

Make it mine, for a long-form opening or a package: write up to n (1 to 5, default 3) new ones for your niche that keep one real find's structure. From a long find, written holds openings: hook (what the creator says first), then (what the next half minute has to deliver) and kept_structure, built on the find's template and its order of beats. From a packaging find it holds packages: title, thumbnail (what to show and how to frame it), thumbnail_text (the words to print, or null) and kept_structure, built on its title template and its thumbnail's composition.

Write my intro: with mode "intro" and video_brief (your own video in a few sentences,
10 to 600 characters; a long find only, a packaging find is 422; niche and n are not
used) it writes YOUR intro in the real opening's structure. `written` then holds one
object with a beat for each beat of the real opening, in order: beat, does, from_s,
to_s, seconds and words_budget (the real opening's own timing, never the model's), say
(the words to say, with {placeholders} for what only you know), words, placeholders,
suggested_on_screen and suggested_broll (suggestions, never part of what is said); and
seconds, timing (measured or estimated), kept_structure, placeholders and
numbers_to_placeholders. The answer carries mode "intro" and video_brief, and niche is
null. A number you did not write in video_brief becomes {number}. One that copies the
real opening or runs over a word budget is 422 remix_not_possible.

Returns {"find_id", "kind", "niche", "n", "written", "label", "credits_charged": 1,
"credits"}. label says they were written by Hook Detector from a real opening's (or
package's) structure: show it with them, never present one as a real video's. One that
is the real find's own words is dropped. They are never added to a run, a keep or an
export. Costs 1 credit per call, taken before the model is asked and refunded when it
does not answer (503 model_unavailable) or when nothing it wrote keeps the rules or it
declines the content (422 remix_not_possible, the reason in the message; another try
or another niche may work). 402 insufficient_credits at a balance of 0;
404 find_not_found; limited per account per hour (429 rate_limited). Needs the
research permission. The answer carries remix_id: list_remixes and get_remix read it
back, free. Same as POST /v1/finds/{find_id}/remix.

Make it mine: write up to n new opening lines (1 to 5, default 3) for your niche that keep a real hook's structure, the device that made it travel, with the subject swapped for yours. hook_id is one of your hooks (from get_run, get_hook or list_keeps); 404 hook_not_found otherwise. Leave mode out: "intro" (Write my intro) is remix_find on a long-form find, and is 422 here, before any charge.

Returns {"hook_id", "niche", "n", "written": [{"line", "kept_structure"}], "label",
"credits_charged": 1, "credits"}. label is always
"Written by Hook Detector from a real hook's structure":
these are written lines, never found hooks; show the label
with them, never present one as a real clip's hook. They are never added to a deck, a
keep or an export. Costs 1 credit per call, taken before the model is asked and
refunded when it does not answer (503 model_unavailable) or when nothing it wrote
keeps the rules or it declines the content (422 remix_not_possible, the reason in the
message; another try or another niche may work). 402 insufficient_credits at
a balance of 0; limited per account per hour (429 rate_limited). Needs the research
permission. The answer carries remix_id: list_remixes and get_remix read it back,
free. Same as POST /v1/hooks/{hook_id}/remix.

Take one video out of a folder; the hook or find and its keep stay. Returns {"item_id", "removed": true}. Same as DELETE /v1/folders/{folder_id}/items/{item_id}. Free. Errors: 404 item_not_found (also on a second remove).

Take a channel off one of your trackers. Same as DELETE /v1/trackers/{tracker_id}/channels/{ref}.

The owner removes a member; anyone leaves with member_id "me". A removed member's next spend comes from their own balance, never the pool. The owner leaving with members is 409 team_has_members; alone it ends the team and returns the pool. Needs admin. Free. Same as DELETE /v1/team/members/{member_id}.

Rename a folder, change its description, or both. A name another folder on the tab already has is 409 folder_exists. Returns the folder. Same as PATCH /v1/folders/{folder_id}. Free.

Ask for the beta access code a new account needs (create_account's access_code). email is where the code is sent; note is optional (who you are, up to 500 characters). The owner approves the request and the code is emailed at once; it works once, in any agent or on the web. Returns status pending (waiting for approval) or emailed (sent now). No key needed. Limited to 5 per address per hour. Free.

Keyword research for YouTube. volume: always estimated (YouTube publishes no search counts): estimated_monthly_searches with a range, a 0 to 100 score and band, its source (Google Trends with the YouTube filter against fixed anchors; or, when Trends is busy, YouTube autocomplete and the top results' views) and basis. competition: 0 to 100 counted from the top 10 long-form results (big channels, posted in the last year, the keyword in the title, how many beat their own channel 2x). score: value 0 to 100 (60% volume, 40% the room competition leaves), band very_low, low, medium, high or very_high (vidIQ's brackets) and the basis naming its inputs. related, questions, rising: terms from autocomplete and the top results' titles, each with its source. Costs 2 credits, refunded when the read fails; a bad request is 422 and costs nothing. Takes about 10 to 30 seconds. Same as POST /v1/keywords. Read it back with get_call.

Edit Review of a cut before upload (25 credits; an unlisted or public YouTube link up to 60 minutes): cuts a minute, long shots, dead air, sound changes, on-screen text, and the notes as Premiere CSV, Resolve EDL and FCPXML markers. Runs as a job. Same as POST /v1/review/edit; to review the file itself (when YouTube refuses our servers the link is refused free with upload_instead), send it to POST /v1/review/edit/upload.

Hook Review of your own opening (3 credits): a YouTube link (its first minute heard by Scribe v2) or a pasted script, scored out of 10 from named counted parts, a verdict per beat, and the promise check against your title and thumbnail words. Same as POST /v1/review/hook.

Script Review (3 credits): your pasted script read like a Video Review on estimated times, plus machine-sounding lines and a fact-check list. Runs as a job. Same as POST /v1/scripts/review.

Rate my Reel or Short: read one public short the way Hook Detector reads a clip (its first frames, its words heard by ElevenLabs Scribe v2) and rate it against the real finds on its subject (the Short form search over the last 30 days, ranked by their multiple over the creator's usual). Returns review_id, url, platform, video_id, subject, subject_from, clip (first_line, first_word_s, words_per_minute, longest_pause_s, words, heard_by, not_heard_why, onscreen_text, plays, multiple), reads (five, in order: stop, gap, momentum, feeling, reach; each with verdict strong, moderate or weak, says, computed_from counted against the finds, and finds: 1 to 3 ids from finds), finds (each a real video with its url, plays, multiple, first_line and pace), finds_from, label, credits_charged and credits. Never a guessed number. Costs 3 credits, taken first and given back on any failure: 422 invalid_link (before any charge), 404 video_not_found (private or removed), 422 not_a_short, 422 review_not_possible (too few finds on the subject), 503 model_unavailable. 402 insufficient_credits under 3; limited per account per hour (429). Takes up to about 90 seconds. Needs research. Same as POST /v1/review/short.

Video Review of any public long video (15 credits): five ranked fixes with times and the counted fact behind each, six sub-scores each with what it is computed from, the hook scored and rewritten (labelled as written), the curve (YouTube's replay peaks, not retention; your Studio curve via graph_points; else predicted, not measured), the story with gap rules, pace and loudness per section, the next five uploads. Runs as a job: answers the paid call (pending); get_call reads it. Same as POST /v1/review.

Owner only: revoke an access code (code_id from list_access_codes). It admits nobody from now on; accounts it already made keep working. 404 access_code_not_found for an unknown id. Free.

Revoke one of your API keys at once: key_id from list_keys, or "original" for the signup key. Any key may revoke itself (the result says so, and that key stops working immediately); revoking another needs admin. Never the last active key on the account (409): create another with create_key first.

If a key leaked, pass key_id "others": every key of the account except the one you
are calling with is revoked at once, and the result says how many (revoked_count) and
which key is kept. Needs admin. Free.

Revoke an open invite: its link stops working at once. Owner only. Needs admin. Free. Same as DELETE /v1/team/invites/{invite_id}.

Check a saved search now, as a job (read it with get_job). 1 credit. Same as POST /v1/alerts/{alert_id}/run.

Save filters under a name for one tab: "long", "packaging" or "library" (the bounds are those of find_packaging's filters; a library preset may also hold min_comments, max_comments, posted_within_days and language). The same name on the same tab replaces it. Start a run from it with preset_id on find_long_hooks or find_packaging. At most 50 an account. Same as POST /v1/presets. Free.

File one video in a folder of its tab: a find (find_id) or any public YouTube video (video_id) in a long or packaging folder, a hook (hook_id) in a short one, with an optional note. A video already in the folder (the same find, another run's find of it, the same hook) returns that item with created false; a note given then replaces its note. Filing does not keep it. Same as POST /v1/folders/{folder_id}/items. Free. Errors: 404 find_not_found or hook_not_found, 422 kind_mismatch, 409 folder_full (2000 items).

Score a package against the real outliers on its subject, part by part (title device, length, words on the picture, faces, the words' role, contrast, brightness): each part says how many outliers it matches; pattern_match (0 to 100) is the mean share: how much the package resembles the subject's outliers, never a click-through rate or a prediction (in our test it scored outliers above their channels' usual videos on about 3 of 4 pairs). Also nearest (5 outliers) and fixes. 1 credit, refunded when the read fails. Same as POST /v1/packaging/score.

Channels by name or handle: the shared index first, then YouTube's own channel search. Free. Same as GET /v1/channels/search.

Search the shared index of public YouTube videos Hook Detector's runs measured, with no run: words by text and meaning, or browse; filters for the multiple, views, long or short, recency, channel size and language. Free. Same as GET /v1/index/search.

Thumbnails in the shared index by what the picture shows (q), or like a picture (image_url: read once by the model as subject, action, words and setting, then searched). Each result has matched_by (text or meaning). Free; image reads at most 60 an hour. Same as GET /v1/index/thumbnails and POST /v1/index/thumbnails/by-image.

Set a member's monthly cap on the pool (null removes it). A run started near the cap holds only what is left, so the cap is never passed mid-run (403 team_cap_reached below a run's minimum or a tool's price). Owner only. Needs admin. Free. Same as PATCH /v1/team/members/{member_id}.

Turn on a folder's share link: share_url is a public read-only page anyone with it opens signed out (hookdetector.com/f/); api_url is the same as JSON (get_shared_folder). It shows the folder's name, description and items with their notes, never anything about the account. A shared folder keeps its link. Same as POST /v1/folders/{folder_id}/share. Free.

Share a finished Short form run as a public, read-only page anyone can open with the link, no sign-in: each hook's spoken line, on-screen words, idea, plays, creator and its video, in the Hook Detector skill page layout. Nothing about the account is on it.

Returns {"run_id", "token", "url"}; give the person the url
(https://hookdetector.com/p/<token>). Idempotent: a run keeps one link, so calling again
returns the same url. The same body as POST /v1/runs/{run_id}/share; the page's data is
GET /v1/shared/{token}, no key needed. Needs the write scope. Free.
Errors: 404 run_not_found, 409 run_not_finished while the run works (call get_run with
wait_seconds=50 first), 409 run_not_shareable for a failed run or a Long form or
Packaging run, 422 invalid_request for a malformed run_id.

Real hooks this service has delivered, for a wait screen: talking heads only, each hook_id, still_url (a JPEG, no key needed), platform, creator, views and line (the banner on the video, else its opening line). The most viewed first, one per creator, only what is already public on TikTok or Instagram: never a topic, an account or a run. No key needed. Cached 10 minutes. Free. REST: GET /v1/showcase?n=12.

Channels in the shared index closest to this one by the meaning of their titles, else by shared words, with a similarity 0 to 1. Free. Same as GET /v1/channels/{ref}/similar.

Start a background job on Hook Detector's job runner. Only echo can be started by hand: it waits seconds and answers message back with how many attempts it took (a job survives a deploy). At most 3 an hour per account. Free. Same as POST /v1/jobs; read it back with get_job.

Your swipe file: the title structures of the Packaging finds you kept or filed, each title_template with its title_device, count (how many of those videos use it, one a video) and best (the example with the highest outlier_score, 0 to 100). The most used first; packages is how many videos were read, skipped how many had no structure. Same as GET /v1/swipe. Free.

Send one signed test delivery now and read what your URL answered. Same as POST /v1/webhooks/{webhook_id}/test.

Where the eye is predicted to land on a thumbnail: the picture with a heatmap over it (PNG, base64), a 16 by 9 grid, the peak, the share in each third, the concentration and the share in YouTube's length corner. UNISAL (AUC 0.895 on MIT1003): faces draw it strongly, printed words less than people read them; a prediction, not a click-through rate. Free. Same as POST /v1/thumbnails/attention.

Your tracker alerts, newest first, with the unread count. Free. Same as GET /v1/trackers/alerts.

A tracker's channels' uploads, strongest first. Free. Same as GET /v1/trackers/{tracker_id}/feed.

Trending Shorts: the short videos (TikToks, Instagram Reels, YouTube Shorts) rising now on a subject, fastest first. Each item has video_id, platform, url, cover_url, creator, caption, plays, posted_at, age_hours, plays_per_hour (plays over the hours since posting, at least one), multiple and multiple_basis (plays over the creator's usual: the median of their latest videos, or TikTok likes per video; null when it could not be measured), creator_usual, duration_s, and spoken_hook with spoken_hook_from (the opening line when one of your own Short form runs delivered the video, or Scribe v2 heard it). At most 20 items, 2 per creator; a video with no post date is never listed. unavailable names a platform whose search did not answer. Free (credits_charged 0); the same subject, platform and window within 30 minutes is served from the cache, and fresh fetches are limited per account per hour (429 rate_limited). 503 search_unavailable when no platform answered. Needs read. Same as GET /v1/shorts/trending.

Turn a folder's share link off: the old link stops working at once; share_folder again makes a new one. Same as DELETE /v1/folders/{folder_id}/share. Free.

Change an agent's name or monthly budget, or pause it. Same as PATCH /v1/agents/{agent_id}.

Change a saved search: its words, line, frequency or email. Same as PATCH /v1/alerts/{alert_id}.

Rename a tracker, share it, change its alert lines, or turn its daily ideas on. Same as PATCH /v1/trackers/{tracker_id}.

Your credits and what you have spent: credits (balance now), spent_total, reserved_now (credits held by runs still in flight, refunded in part when they finish), runs_total, last_30_days (one entry per UTC day: date, runs, charged) and recent (your 20 newest runs). Same shape as GET /v1/usage. Free.

Badges for up to 50 YouTube videos at once, as the Chrome extension shows them on every card: views, the multiple over the channel's usual views (long against long uploads, Shorts against Shorts) with its band, and views per hour with its basis. Ids with no badge are in unread with why. Free. Same as GET /v1/videos/badges.

Everything the index knows about one video: the multiple, views per hour and its history, real tags, title and thumbnail changes, our reads, similar videos. Free. Same as GET /v1/videos/{video_id}/scorecard.

A video's views per hour and its history from the shared index (new, rising and tracked videos read hourly, the rest daily); a video the index lacks is read now. Free. Same as GET /v1/videos/{video_id}/stats.

What an invite joins, before accepting: the team's name, who invited you, its seats, when the link expires, and whether you are signed in with the invited email (null for an account with no email). Free. Same as GET /v1/team/invites/{token}.

Vote on a poll with the slot you picked, and an optional reason. One vote an account, never on your own or your team's poll. Answers the shares so far. Free. Same as POST /v1/polls/{poll_id}/vote.

A webhook's deliveries, newest first, with status and your URL's answers. Same as GET /v1/webhooks/{webhook_id}/deliveries.

Hook Creator (1 credit): an opening for your subject as beats with seconds counted from their words and a shot plan per line (said, shown, on screen, sound, delivery), labelled as written. Same as POST /v1/openings.

Write ideas for new videos: each a title, a thumbnail concept (one visible action) and the words to print, built on one to three real outliers (based_on, each with its video_id, title, multiple, find_id and bend niche when it came from another niche). constraints are rules every idea keeps (said in fits). band (10x, 5x, 2x) is the median multiple of the finds behind the idea, never a predicted view count. label: written by Hook Detector. 1 credit, refunded when the writing fails; fewer than 5 outliers known is 422 too_few_outliers and costs nothing. Same as POST /v1/ideas; remix_find makes one find yours.

Script Writer (10 credits): hooks, the plan's sections with re-hooks and payoffs, the script, its runtime counted from its words, machine-sounding lines flagged, a fact-check list, Markdown. Runs as a job (get_call reads it). Same as POST /v1/scripts.

Write 20 to 40 titles for your video, each borrowing the device and structure of one real outlier (a video that beat its own channel): the finds of one of your runs, or the shared index's videos nearest your topic by meaning. Each title: title, chars, first_40 (what a phone feed surely shows), device, borrows, and from (the real outlier: video_id, title, channel, multiple, find_id). best: the five whose outlier beat its channel the most among the devices the outliers share (best_basis says so; never a predicted click-through rate). label: written by Hook Detector, never a real video's title. Costs 1 credit, refunded when the writing fails; fewer than 5 outliers known is 422 too_few_outliers and costs nothing (run find_packaging on the topic first). Same as POST /v1/titles. Read it back with get_call.

The upload pack (1 credit) for a long find or your video: a description with chapters that pass YouTube's rules, tags and hashtags. Runs as a job. Same as POST /v1/seo.