“What hooks are working in our niche right now?”
The opening lines of top videos, typed by hook and ranked by engagement rate.
Ask Claude or ChatGPT what people on TikTok say about your product, your competitors or your category. buzzabout finds the relevant videos, transcribes them, reads the comments and hands back the answer with sources.
Free trial with 1,000 credits. Copy page as Markdown Open in Claude
I read 200 recent skincare videos and their comments. Three hooks lead on engagement: before/after reveals ("Day 1 vs day 30"), ingredient myth-busting ("Stop using retinol like this") and honest reviews that open on a complaint. The question viewers ask most: how long until results show. Want the top 10 videos for each hook?
Ask in plain English. Get answers with sources.
The opening lines of top videos, typed by hook and ranked by engagement rate.
Questions and objections from up to 100 comments per video, grouped into themes.
Creators, engagement and the sentiment of the comments under their videos.
Videos labeled by format on request, with engagement compared across formats.
Sentiment and emotions across every video, with the lines that set the tone.
buzzabout proposes a weekly tracking agent. Confirm it in the app and it collects and analyzes new videos on schedule.
Every TikTok post arrives transcribed, labeled and ready to use. Fifteen MCP tools do the work.
{
"source": "tiktok",
"url": "https://www.tiktok.com/@example.creator/video/7431...",
"text": "30 days of bakuchiol instead of retinol #skincare",
"summary": "Creator switched from retinol to bakuchiol after irritation and reports calmer skin after 30 days.",
"hooks": [
{
"type": "Story Opening / Narrative",
"text": "My skin could not handle retinol anymore"
}
],
"content_topics": [
{
"text": "retinol alternatives"
},
{
"text": "sensitive skin"
}
],
"questions": [
{
"text": "Does bakuchiol work as well as retinol?"
}
],
"sentiment": {
"positive": "0.78",
"neutral": "0.17",
"negative": "0.05"
},
"emotions": {
"joy": "0.55",
"surprise": "0.30",
"neutral": "0.15"
},
"tone_of_voice": {
"text": "candid",
"evidence": "Honest results"
},
"narrative_structure": {
"text": "before/after transformation",
"evidence": "DAY 1 vs DAY 30"
},
"cta": {
"text": "comment/engage",
"evidence": "Tell me if you want the full routine"
},
"media": [
{
"type": "video",
"version_list": [
{
"duration_millis": 41200
}
],
"transcription": "My skin could not handle retinol anymore, so...",
"on_screen_text": "DAY 1 vs DAY 30",
"description": "Selfie video, side-by-side skin comparison"
}
],
"created_at": 1793433600,
"dataset_run_at": 1793836800,
"content_analyzed_at": 1793837100,
"author": {
"title": "@example.creator",
"headline": "Example Creator"
},
"num_views": 184300,
"are_views_estimated": false,
"num_likes": 12940,
"num_comments": 611,
"num_shares": 402,
"engagement_rate": "0.076",
"sound": {
"name": "original sound",
"author": "example.creator"
},
"category": "style_and_fashion",
"vibe": {
"raw_authentic": 0.8,
"aspirational": 0.2
},
"speech_tempo": "medium",
"music_genre": "no_music",
"language": "en"
}15 MCP tools
askAsk a research question in plain English; get a cited answer.get_messageRead the research agent's answer as it lands.collect_mentionsPreview a topic, then collect and analyze the posts.ingest_mentionSave and analyze one public post by URL.get_runFollow any run's progress, with long-polling.get_save_mention_statusTrack a saved post's analysis.queryAsk your data anything: counts, themes, trends, comments, audience.list_mentionsRead collected posts with all their AI fields.detect_patternsGroup posts into 2 to 15 named themes.collect_audienceProfile the people commenting, in aggregate (Pro and up).renderShow answers as interactive charts and tables.list_tracking_agentsSee your scheduled topic trackers.get_tracking_agentRead one tracker and what it found.list_collectionsSee everything you have collected.get_meCheck your plan and credit balance.media[].transcriptionThe spoken words, transcribed.media[].on_screen_textText burned into the frames, read by OCR.media[].descriptionWhat happens in the video, described by AI.speech_tempoSlow, medium or fast delivery.hooksHook type plus the exact opening line.narrative_structureStory shape, with the quote that shows it.creative_formatOne of 22 formats, such as talking head, tutorial, before/after or unboxing. On request.ctaThe call to action, with evidence.content_intentionInform, entertain, sell or engage.vibeTwelve mood scores, from raw and authentic to corporate.music_genreGenre of the background track.summaryA short summary of the video.content_topicsThe topics it covers.questionsQuestions asked in the video.mentioned_brandsBrands named in speech, caption or on screen.entitiesPeople, places, events and organizations named; brands are in mentioned_brands.sentimentPositive, neutral and negative shares.sentiment_scoreOne number from negative to positive.emotionsJoy, surprise, anger, sadness, fear, disgust, neutral.tone_of_voiceTone label with the line that sets it.num_viewsReal play count from TikTok.num_likesLikes.num_commentsComment count.num_sharesShares.engagement_rate(likes + comments + shares) / views, computed for you.comments[].bodyThe comment text.comments[].num_likesLikes on the comment.comments[].num_repliesHow many replies it drew.comments[].created_atWhen it was posted.comments[].sentimentHow each comment feels, scored (via query).Read comments through MCP query or buzzabout__ask. They are not in list_mentions or the REST response yet.
Also in every record: url, text, author.title, author.avatar, media[].version_list, media[].version_list[].duration_millis, media[].cover_image, sound, created_at, dataset_run_at, content_analyzed_at.
Other data providers give you raw posts. buzzabout gives you answers.
| Capability | buzzabout | Other data providers |
|---|---|---|
| What you get back | YesPosts already read, labeled and grouped into themes | NoRaw posts |
| Works in Claude, ChatGPT and other AI agents | YesOne MCP connection, every plan | YesRaw-data MCP servers |
| All 7 platforms in one request | YesOne question covers all 7 | PartlyOne scraper per platform |
| Off-topic posts filtered, never billed | YesAI check on every post | NoYou pay for every record returned |
| Transcripts and on-screen text | YesEvery video, included | PartlyPaid add-ons on some tools |
| Hooks, topics, sentiment and tone | YesOn every post | NoBring your own AI |
| Comments with every post | YesUp to 100 per post, included | PartlySeparate scraper, billed per comment |
| Themes across many posts | Yes2 to 15 named themes per question | NoNone |
| Price | Starting at $49, everything included | From about $472 a month for the full stack |
Bought separately, the same stack costs about $472 a month, before anyone builds anything.
What buzzabout includes
MCP on every plan. REST API on Business.
Add buzzabout as a connector and ask in plain English. That's it.
https://mcp.buzzabout.ai/mcp and sign in.Install the MCP server and let Claude Code build on it: digests, dashboards, alerts.
claude mcp add --transport http buzzabout https://mcp.buzzabout.ai/mcp.1. In Claude, add a custom connector.
2. URL: https://mcp.buzzabout.ai/mcp
3. Sign in, then ask:
"What do people on TikTok say about
switching from retinol to bakuchiol?"1. In ChatGPT, add a custom connector (MCP server).
2. URL: https://mcp.buzzabout.ai/mcp
3. Sign in, then ask:
"What do people on TikTok say about
switching from retinol to bakuchiol?"claude mcp add --transport http buzzabout https://mcp.buzzabout.ai/mcp
# then, in Claude Code:
> Build a weekly digest of TikTok posts about
switching from retinol to bakuchiol, with the top hooks, questions
and sentiment, posted to our Slack webhook.{
"mcpServers": {
"buzzabout": {
"url": "https://mcp.buzzabout.ai/mcp"
}
}
}curl -X POST https://api.buzzabout.ai/v1/ask \
-H "x-api-key: $BUZZABOUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"message": "What do people on TikTok say about switching from retinol to bakuchiol?"}'Every plan includes the MCP and the full analysis.
2,000 credits a month. Up to 250 posts per research.
Try for free5,000 credits a month. Audience research. Up to 1,000 posts per research.
Try for free20,000 credits a month. REST API. Unlimited listening agents.
Try for freeFree trial with 1,000 credits. A card is needed to sign up. See pricing.
buzzabout. Connect it to Claude or ChatGPT and every TikTok video comes back transcribed, read and labeled, with comments and up to 17 analysis actions, through one connection that covers six other platforms. A typical run is ready in 3.5 minutes, 99% of runs complete, and you pay only for videos you keep.
No. TikTok limits the Research API to academic and non-profit researchers in a few regions, and it forbids commercial use. buzzabout is built for brands, agencies and startups. Try it free.
Not from TikTok if you are a business: its Research API is only for approved academic researchers. buzzabout transcribes the speech in every video and reads the on-screen text, and returns both with the post, at no extra cost.
Yes. buzzabout collects up to 100 top-level comments per video at no extra cost, with likes, reply counts, timestamps and sentiment. Ask Claude or ChatGPT about them in plain English, or query them through the MCP.
A scraper hands you raw TikTok records and stops. Transcription, on-screen text, relevance filtering, labeling and storage are separate tools you buy, connect and maintain. Add themes, scheduled runs, memory and integrations and the full stack starts at about $472 a month, before anyone builds anything. buzzabout includes all of it, starting at $49, through one connection your agent already speaks.
Starting at $49 for your first month on Starter, then $98 a month. Each post you keep costs one credit, with the analysis included. See pricing.
Yes. Add buzzabout as a custom connector in ChatGPT with https://mcp.buzzabout.ai/mcp and sign in. Custom connectors depend on your ChatGPT plan.
No. You pay only for the posts you keep.
No. Add buzzabout to Claude or ChatGPT and ask in plain English. Growth engineers can use the same MCP in Claude Code or Cursor.
Start a free trial with 1,000 credits, add buzzabout to Claude or ChatGPT and ask your first question.
Free trial. Works in Claude and ChatGPT.