Podcast & Audio Transcript — speakers, chapters, summary, SRT/VTT

🎁 Free trial until Nov 20, 2026: your first 60 audio minutes are free — enough for a full episode with speakers, chapters, summary and subtitles. After that, $0.008 per minute.

Paste a podcast episode, YouTube video or MP3/M4A link and get a speaker-labeled transcript with chapters as clean JSON — ready for show notes, YouTube chapters, subtitles, blog posts or RAG.

You get	Details
🗣️ Who said what	Transcript split into turns by speaker (S1, S2 …), number of speakers detected automatically
🎭 Speaker roles	Host / guest guessed from context, with names only when they are actually said
📚 Chapters	Topic chapters with start times (00:12:24 Sponsor segment) — paste straight into YouTube
📝 Summary & topics	Episode summary bullets and keywords
🎬 Subtitles	Ready-to-use SRT and VTT with speaker tags
🌐 Translation (optional)	Whole transcript translated, timestamps and speakers kept (ja, es, de, fr, pt-BR, zh, ko …)

Why this one

• Simple pricing: $0.008 per audio minute — a 1-hour episode with speakers, chapters, summary and subtitles is $0.48, all included. Failed or private links are free.
• Accurate. Speech model measured at 2.2% word error rate on human-captioned talks. Speaker count detected correctly on 10 of 11 test recordings, including real 4-person meetings (AMI corpus).
• Long audio. Up to 3 hours per file, 99 languages auto-detected.
• Fast. A 12-minute episode takes about 1 minute (2 with translation); 46 minutes about 4 minutes.

Input

{ "audioUrls": ["https://www.youtube.com/watch?v=6n7pebYrbvQ"], "speakers": 0, "diarization": true, "translateTo": "" }

speakers: set it if you know it (2 = host + guest), 0 = automatic.

Output (one item per episode)

{
  "source": "https://www.youtube.com/watch?v=6n7pebYrbvQ",
  "status": "ok", "language": "en", "duration": 722.3,
  "speakers": ["S1", "S2", "S3", "S4"],
  "speaker_roles": [{"speaker": "S1", "role": "Host: Marco"}, {"speaker": "S2", "role": "Host: Erika"}],
  "chapters": [
    {"start": 0, "timestamp": "00:00:00", "title": "Introduction and Vocabulary Preview", "summary": "…"},
    {"start": 70, "timestamp": "00:01:10", "title": "Dialogue: Watching a Basketball Game", "summary": "…"}
  ],
  "summary": ["…"], "topics": ["…"],
  "turns": [{"speaker": "S1", "start": 1.1, "end": 9.0, "text": "Hello, English learners. Welcome back to EnglishPod…"}],
  "segments": [{"start": 1.1, "end": 4.52, "text": "…", "speaker": "S1"}],
  "text": "S1: Hello, English learners…\nS2: That's right…",
  "srt": "1\n00:00:01,100 --> 00:00:04,520\n[S1] Hello, English learners…",
  "vtt": "WEBVTT\n\n00:00:01.100 --> …",
  "translation": {"lang": "ja", "text": "[1s] S1: 英語学習者の皆さん、こんにちは…"}
}

Pricing (pay per event)

• Audio minute (transcript + speakers + chapters + summary + SRT/VTT): $0.008 per started minute
• Translation minute (only if translateTo is set): +$0.003 per minute

Use cases

• Podcast show notes, chapters and episode pages
• YouTube chapters and multi-language subtitles
• Interview and meeting minutes with speaker attribution
• Feeding AI agents / RAG with long-form audio (works with the Apify MCP server)

Notes

• Public links only. Overlapping speech is attributed to the main speaker. Speaker labels are anonymous (S1, S2); roles are a best guess from the conversation.
• Short-form video with on-screen text and hook analysis? See our Video Transcript + On-screen Text + Hook & Summary AI actor.

More tools from Brain Spice

• Video Transcript + On-screen Text + Hook & Summary AI — TikTok / Reels / Shorts breakdown, $0.01 per video
• Podcast & Audio Transcript with Speakers, Chapters, SRT — who said what + chapters, $0.008 per minute
• YouTube Comments AI Analyzer — sentiment, viewer questions, content ideas, $1 per 1,000 comments

Use it from code, n8n, Make or an AI agent

API (one call, waits for the result):

curl -X POST "https://api.apify.com/v2/acts/vidlens~podcast-transcript-speakers-chapters/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"audioUrls": ["https://www.youtube.com/watch?v=..."]}'

Python:

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("vidlens/podcast-transcript-speakers-chapters").call(run_input={"audioUrls": ["https://www.youtube.com/watch?v=..."]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

• n8n: use the Apify node → "Run actor and get dataset", actor vidlens/podcast-transcript-speakers-chapters.
• Make / Zapier: use the Apify app → "Run an Actor", then "Get dataset items".
• AI agents (Claude, ChatGPT, Cursor): available through the Apify MCP server (https://mcp.apify.com) — add vidlens/podcast-transcript-speakers-chapters as a tool.