Type a podcast name and get its newest episodes as text, with timestamps and optional speaker labels. Schedule it to receive only new episodes.
podcastFeeds: names, Apple Podcasts links or RSS URLs.speakerLabels: true marks Speaker 1, Speaker 2…maxDurationMinutes caps cost on long shows.from apify_client import ApifyClient # pip install apify-client
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("fguiraud/podcast-transcript-scraper").call(run_input={
"podcastFeeds": [
"NPR News Now"
],
"maxEpisodesPerFeed": 2,
"outputs": [
"text"
]
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item["podcast"], "-", item["episodeTitle"])
No Python? Open the Actor page, paste your input in the form and press Start; results export to JSON, CSV or Excel.
Fields from a real run on 2026-09-24 (long values shortened):
{
"podcast": "NPR News Now",
"episodeTitle": "NPR News: 09-24-2026 1AM EDT",
"published": "2026-09-24T05:10:11+00:00",
"status": "ok",
"language": "en",
"durationSeconds": 280.06,
"billedMinutes": 3,
"text": "Live from NPR News on July, Snyder. Australia's Prime Minister says an AI agent created by OpenAI infiltrated a government website. The government says the incident occurred in June, but Christina Cuculio reports that Op..."
}
$0.006 per audio minute; speaker labels add $0.003 per minute. A 60-minute episode costs $0.36.
Is silence billed?
Billing is per transcribed minute, rounded up per episode.
Can I transcribe a whole back catalog?
Yes, raise maxEpisodesPerFeed; check the cost estimate first.
Can an AI agent use it?
Yes. It is an MCP server at https://mcp.apify.com/?tools=fguiraud/podcast-transcript-scraper (listed in the official MCP registry), and there is an agent skill for Claude Code, Codex and Cursor. Field-name guesses such as url or urls are accepted.