Podcast & Media Intelligence

Turn podcasts, interviews, and recordings into speaker-separated transcripts, subtitles, summaries, chapters, and show notes — powered by Gemini 3.5 Transcribe (85+ languages). Automation-ready JSON for n8n, Make, webhooks, and AI agents.

Store: apify.com/kondasviktor/podcast-media-intelligence

PPE: $0.025 / audio minute + $0.99 content package · min $0.10 · + Apify usage

What it does

• Direct media URL or podcast RSS (latest / latest N / filter)
• Smart or verbatim transcription, speaker diarization, segment timestamps
• SRT / WebVTT in key-value store; structured dataset JSON
• Content package: summary, chapters, topics, entities, quotes, show notes
• RSS dedup (skipPreviouslyProcessed + stateKey) for scheduled weekly runs
• Preview mode (previewMinutes: 3) for low-cost trials
• Up to 30 minutes per source in v1

Who it's for

• Podcasters and media teams
• Agencies repurposing long-form audio
• Automation builders (Apify schedules → CMS / newsletter)
• Multilingual workflows (e.g. Hungarian audio → English show notes via targetLanguage: en)

What this Actor is — and is not

• Is: audio intelligence pipeline with platform-managed Gemini (no API key required from users).
• Is not: a YouTube downloader, video clip renderer, or legal/certified court transcription service.
• You must have rights to process the audio you submit.

Pricing

Event	Price
Audio minute	$0.025
Content package (per episode)	$0.99
Minimum	$0.10

28-minute episode with package ≈ $1.69 (+ usage).

Failed runs are not charged.

Limitations (v1)

• Direct media URLs only — YouTube / podcast page URLs are not supported. Pass a direct https://…mp3|m4a|wav|mp4|webm|ogg link (or RSS enclosure).
• previewMinutes — used for billing estimate and to skip the content-package charge. It does not yet trim the audio sent to Gemini.
• Long files (~20+ min) — full transcript is usually accurate; segment timestamps / SRT can be coarse (often one large segment). Finer segmentation is planned.
• Max 30 minutes per source in v1.
• Process only audio you have rights to use.

Quick start — preview (public-domain sample)

Public-domain FDR “Day of Infamy” speech (Internet Archive). Use previewMinutes to keep trial cost low:

{
  "mediaUrl": "https://archive.org/download/FDRDayOfInfamySpeech/President%20Franklin%20Roosevelt%2527s%20%22Day%20of%20Infamy%22%20Speech%2C%2012%3A08%3A1941.mp3",
  "previewMinutes": 3,
  "contentPackage": false,
  "outputs": ["srt", "vtt"]
}

Full episode with intelligence

{
  "mediaUrl": "https://example.com/episode.mp3",
  "language": "auto",
  "targetLanguage": "en",
  "contentPackage": true,
  "customVocabulary": ["Apify", "Számlázz.hu", "Neon"]
}

Put it on a schedule (recurring revenue)

{
  "rssUrl": "https://example.com/feed.xml",
  "episodeMode": "latest_n",
  "episodeLimit": 3,
  "skipPreviouslyProcessed": true,
  "stateKey": "MY_PODCAST_STATE",
  "contentPackage": true
}

Create an Apify schedule (e.g. weekly). Already-processed episodes are skipped with 0 Gemini cost.

Hungarian → English show notes

{
  "mediaUrl": "https://example.com/hu-episode.mp3",
  "language": "hu-HU",
  "targetLanguage": "en",
  "contentPackage": true
}

Local development

cd apify/gemini-audio-engine && npm install && npm test
cd ../podcast-media-intelligence
cp .env.example .env   # add GEMINI_API_KEY (paid tier)
npm install
npm run dry-run

MCP / automation

Dataset fields are stable: transcription, intelligence, files.markdownKey, usage.eventsCharged. Use Apify MCP or dataset webhooks to feed n8n/Make.

Related actors (suite)

All Actors: apify.com/kondasviktor

Actor	Role
Podcast & Media Intelligence (this Actor)	Transcripts, show notes, SRT/VTT
Meeting Intelligence	Decisions, tasks, owners
Google Maps CEE Scraper — Supplier Shortlist	CEE supplier shortlists
Website Intelligence + Contact Extractor	Contacts, tech stack
Dealer / Distributor Locator Extractor	Brand locator pages
PDF Procurement Document Extractor	Certs, reports, datasheets
Website Change Monitor — Diff Tracker	Hash + diff watch
European Fuel Station Prices API (CEE + DACH)	Fuel by country/point/route
Product Catalog Scraper	Catalogs → Shopify / Woo CSV
Wildfire Intelligence API	US + EU wildfire data

Feedback

Contact · Built by Vibe Coder's Life