# Podcast Transcript with Speaker Diarization, Chapters & SRT (`vidlens/podcast-transcript-speakers-chapters`) Actor

Long audio or video URL in, speaker-labeled transcript out: who said what, auto chapters with timestamps, episode summary, SRT/VTT subtitles and optional translation. Podcasts, YouTube, MP3/M4A links. Up to 3 hours.

- **URL**: https://apify.com/vidlens/podcast-transcript-speakers-chapters.md
- **Developed by:** [Brain Spice](https://apify.com/vidlens) (community)
- **Categories:** AI, Videos
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $8.00 / 1,000 audio minute processeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 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

```json
{ "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)

```json
{
  "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](https://apify.com/vidlens/video-understanding) — TikTok / Reels / Shorts breakdown, $0.01 per video
- [Podcast & Audio Transcript with Speakers, Chapters, SRT](https://apify.com/vidlens/podcast-transcript-speakers-chapters) — who said what + chapters, $0.008 per minute
- [YouTube Comments AI Analyzer](https://apify.com/vidlens/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):**

```bash
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:**

```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.

# Actor input Schema

## `audioUrls` (type: `array`):

Podcast episode pages, YouTube videos, or direct MP3/M4A/WAV links. Up to 3 hours each.

## `speakers` (type: `integer`):

Set it if you know it (e.g. 2 for host + guest). Leave 0 to detect automatically.

## `diarization` (type: `boolean`):

Split the transcript by speaker (S1, S2...). Turn off for single-speaker audio.

## `translateTo` (type: `string`):

Language code such as ja, es, de, fr, pt-BR, zh, ko. Leave empty for no translation.

## Actor input object example

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

# Actor output Schema

## `results` (type: `string`):

One item per episode: speaker-labeled turns and segments, chapters, summary, topics, speaker roles, SRT and VTT subtitles, plain text, optional translation, and status/error.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "audioUrls": [
        "https://www.youtube.com/watch?v=6n7pebYrbvQ"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("vidlens/podcast-transcript-speakers-chapters").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "audioUrls": ["https://www.youtube.com/watch?v=6n7pebYrbvQ"] }

# Run the Actor and wait for it to finish
run = client.actor("vidlens/podcast-transcript-speakers-chapters").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "audioUrls": [
    "https://www.youtube.com/watch?v=6n7pebYrbvQ"
  ]
}' |
apify call vidlens/podcast-transcript-speakers-chapters --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,vidlens/podcast-transcript-speakers-chapters"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/G5yV9zFMRlD29oOwu/builds/MnvW6NQf9emglR75P/openapi.json