B2B Social Video Transcripts
Last updated November 13, 2026
Transcripts from TikTok, Instagram Reels, Facebook Reels, X, Threads, podcasts, and Wistia, with pain points, buying signals, competitor mentions, and icebreakers for outbound. Watch creators for new videos. Your own speech and AI keys.
Features
- Transcripts from 7 sources
- Pain points, buying signals, icebreakers
- Watch lists for new videos
- Your own speech and AI keys
- Pay per event: Video transcript at $0.025.
Input
modestringoptionaltranscript (default): transcript, caption, creator, and counts for each video given. outbound: the same plus pain points, buying signals, competitor mentions, and icebreakers on your AI key. watch_list: checks creators, podcast feeds, podcast keywords, and Threads hashtags for videos earlier runs have not seen, and transcribes only those.
video_urlsarrayoptionalTikTok video, Instagram reel, Facebook reel, X post, Threads post, podcast episode or RSS feed, Wistia page, or YouTube video URLs. A podcast feed URL reads its latest episodes, up to max_videos_per_creator.
creatorsarrayoptionalwatch_list mode: profile URLs or platform:handle, for example instagram:hubspot, x:gong_io, facebook:HubSpot, threads:hubspot. TikTok has no creator feed without a login, so TikTok creators are refused with a free row.
podcast_feedsarrayoptionalPodcast RSS feed URLs. In watch_list mode each feed is watched for new episodes; in the other modes the latest episodes are read.
podcast_keywordsarrayoptionalwatch_list mode: search terms for finding podcast feeds through the iTunes search API; each feed found is watched.
hashtagsarrayoptionalwatch_list mode: Threads hashtags, without #. Hashtag pages on TikTok, Instagram, X, and Facebook need a login or do not list newest first, so only Threads is read.
wistia_idsarrayoptionalWistia media IDs, or company page URLs that embed Wistia videos; the page is scanned for embedded media IDs.
include_commentersstringoptionalyes or no (default no). On TikTok videos at or above webhook_min_score, adds one row per commenter: handle, name, profile URL, comment, time, likes.
watch_list_namestringoptionalNames the stored watch list. Rows are also appended to a named dataset b2b-social-video-transcripts-<name>, and seen video IDs are kept in a named key-value store b2b-social-video-transcripts-<name>-state. Letters, numbers, and dashes; up to 30 characters. Default default.
watch_list_depthstringoptionaltranscript (default) or outbound: what runs on each new video in watch_list mode.
max_videos_per_creatorstringoptionalMost videos read per creator, feed, keyword result, or hashtag in one run. Default 10, up to 100.
since_daysstringoptionalSkips videos older than this many days. Default 30.
topic_filterarrayoptionalKeywords. A video whose caption, hashtags, and title match none of them is skipped before any speech-to-text call, as a free skipped_off_topic row.
transcript_filterarrayoptionalKeywords matched against the spoken words. Rows are kept, with transcript_match true or false.
stt_providerstringoptionalopenai (default), groq, deepgram, or assemblyai. Used for videos with no native subtitle or transcript.
stt_api_keystringoptionalYour own key for the provider above. Without a key, only videos with native subtitles or transcripts are transcribed; the rest return a free no_speech_track row. Never stored or logged.
stt_modelstringoptionalOptional. With openai the default is gpt-4o-mini-transcribe in transcript mode and whisper-1 when timestamps are needed (outbound mode or include_segments yes), because only whisper-1 returns timestamps among OpenAI models.
stt_fallback_providerstringoptionalOptional second provider, tried when the first refuses or fails.
stt_fallback_api_keystringoptionalYour own key for the fallback provider.
ai_providerstringoptionalopenai (default), anthropic, or gemini. Used by outbound mode and for translation.
ai_api_keystringoptionalYour own key for the AI provider. Without it, outbound mode returns transcripts only and charges no outbound-insights. Never stored or logged.
ai_modelstringoptionalOptional override. Defaults: gpt-4.1-mini (openai), claude-haiku-4-5 (anthropic), gemini-2.5-flash (gemini).
my_companystringoptionalYour company name, so pain points and icebreakers fit your offer.
my_productstringoptionalWhat you sell, in one line.
competitorsarrayoptionalBrand names to flag when spoken. Each is matched exactly in the transcript and by the AI call.
translate_to_englishstringoptionalyes or no. Default yes in outbound mode, no in the other modes. Needs the AI key.
include_segmentsstringoptionalyes or no (default no). Adds transcript_segments to each row. Outbound mode always fills them when the source gives timestamps.
youtube_transcript_providerstringoptionalscrapecreators, searchapi, or supadata. YouTube videos are transcribed only through your own key with one of these services.
youtube_transcript_api_keystringoptionalYour own key for the YouTube transcript provider above. Without it, YouTube URLs return a free row.
youtube_transcript_fallback_providerstringoptionalOptional second YouTube transcript provider.
youtube_transcript_fallback_api_keystringoptionalYour own key for the fallback YouTube provider.
webhook_urlstringoptionalOptional. Each new video row with buying_signal_score at or above webhook_min_score is sent here as a POST with a Slack compatible text field.
webhook_min_scorestringoptional0 to 100. Default 0 sends every video row.
max_charge_usdstringoptionalOptional. The run stops before a charge that would pass this amount. Summary rows are always returned.
Output schema
{
"row_type": "string",
"platform": "string",
"video_url": "string",
"video_id": "string",
"post_type": "string",
"creator_handle": "string",
"creator_name": "string",
"creator_url": "string",
"creator_followers": "integer",
"posted_at": "string",
"duration_seconds": "number",
"caption": "string",
"hashtags": "array",
"mentions": "array",
"play_count": "integer",
"like_count": "integer",
"comment_count": "integer",
"share_count": "integer",
"save_count": "integer",
"transcript_text": "string",
"transcript_segments": "array",
"transcript_source": "string",
"language": "string",
"transcript_english": "string",
"transcript_match": "boolean",
"opening_hook": "object",
"company_mentions": "array",
"product_mentions": "array",
"competitor_mentions": "array",
"pain_points": "array",
"questions_asked": "array",
"buying_signals": "array",
"buying_signal_score": "integer",
"icebreakers": "array",
"topics": "array",
"watch_list_name": "string",
"first_seen_at": "string",
"video_status": "string",
"new_videos": "integer",
"commenter_handle": "string",
"commenter_name": "string",
"commenter_url": "string",
"comment_text": "string",
"comment_posted_at": "string",
"comment_like_count": "integer",
"row_status": "string",
"error_reason": "string",
"billable_events_json": "string",
"scraped_at": "string"
}Pricing
| Event | Free plan price |
|---|---|
| Video transcript | $0.025 |
| Transcript minute after 3 | $0.008 |
| Outbound insights | $0.02 |
| Creator check | $0.005 |
| Instagram creator check | $0.045 |
| Commenter row | $0.002 |
| Actor Start | $0.0085 |
Pay per event on the Apify platform. Paid Apify plans pay less per event. No subscription, no seat license.
On the Apify free plan the actor stops at $1.50 of charges a month, about 60 videos. Any paid Apify plan removes the cap.
Limits
- Hashtag watch lists run on Threads only. TikTok, Instagram, and X hashtag pages need a login or signed requests; Facebook hashtag pages do not list newest first.
- TikTok creators cannot be watched. TikTok's creator list needs signed requests. Give TikTok video URLs in transcript or outbound mode.
- TikTok subtitles exist on about 3 of 5 videos. The rest need your speech-to-text key.
- X lists are curated, not newest first, so a new X video can show up a few runs late.
- Threads post URLs are read through the creator's profile feed, because a single post page carries no post data without a login.
- YouTube transcripts need your own key with ScrapeCreators, SearchAPI, or Supadata. Without one, YouTube rows are free no_speech_track rows.
- Long videos on OpenAI's gpt-4o transcribe models: MP3 audio is split into about 4 minute pieces. A video file cannot be split without transcoding, so a video over about 4 minutes runs on whisper-1 instead, and OpenAI and Groq take files up to 25 MB. Deepgram and AssemblyAI take larger files.
- Buyer key routes: no Mamba Labs key is used for Groq, Deepgram, AssemblyAI, Anthropic, Gemini, ScrapeCreators, SearchAPI, or Supadata. Those routes are tested on recorded responses and on the refused key path; your first run with your key is the live test.
- Watch lists fill back in time. Each run takes up to max_videos_per_creator unseen videos per creator inside since_days, newest first. With a wide since_days, later runs keep picking up older videos until the window is used up. Keep since_days short (the default is 30) to transcribe only new videos.
- TikTok commenters: up to 200 comments per video, read from TikTok's public comment list. Each commenter row is charged, so set webhook_min_score to limit commenters to high scoring videos.
- Threads videos carry no length in the public page, so Threads rows leave duration_seconds empty and are never charged extra minutes.
- A refused page is final. A 403, 429, or challenge page returns a free blocked row; the actor does not retry on another network to get around it. X answered 429 on 1 of 6 creator checks in testing.
- Speech-to-text keys tested live: OpenAI only (whisper-1 and gpt-4o-mini-transcribe), and the outbound fields on OpenAI gpt-4.1-mini.
- Wistia videos are found from your input only. Give media IDs or page URLs that embed Wistia; search engines do not list them.