# Yt Ai Summarizer (`automify/yt-ai-summarizer`) Actor Turn any public YouTube video URL into multilingual transcript, subtitles, timing data, and AI summary for faster content reuse and analysis. Automatic language detection with clean segmentation and precise timings generated in one run: plain transcript, SRT, VTT, TSV - **URL**: https://apify.com/automify/yt-ai-summarizer.md - **Developed by:** [Krzysztof](https://apify.com/automify) (community) - **Categories:** Agents, Videos, Automation - **Features:** Limited permissions - **Stats:** 21 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $0.05 / 1,000 results 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 ## YouTube AI Transcriber Actor ### What does YouTube AI Transcriber do? **YouTube AI Transcriber** automatically turns any public YouTube video URL into clean transcripts and subtitle files. Provide a single **video URL** as input and the Actor handles audio retrieval, speech recognition, language detection, segmentation and AI summary generation for you on the Apify platform. Use it to quickly transcribe long videos, extract study notes, get quotable lines, prepare timed captions, or obtain an instant AI-generated summary—without manual effort. ### Why use this Actor? Long-form video is time-consuming to consume. This Actor lets you convert video speech into structured text you can filter, search, and reuse. It accelerates: - Content research & editorial workflows - Lesson and lecture preparation - Journalism & fact extraction - Study note creation & revision aids - Competitive analysis & market scanning - Accessibility (captions / alternative formats) Running on Apify gives you scheduling, monitoring, API access, proxy management, webhooks, integrations, and scalable storage—so you can automate batch processing, trigger downstream pipelines, and export results in multiple formats reliably. ### Key Features - **AI-Powered Summaries** (optional): Generate intelligent summaries of transcripts using advanced AI models. - Automatic language detection (no need to specify language; override supported if desired). - Clean segmentation with precise start/end timings for each text block. - Multiple export formats generated in one run: plain text, subtitles (SRT / VTT), tabular timing data, structured JSON. - Dataset + Key‑Value Store outputs for easy API retrieval and automation. - Designed for single-URL simplicity—just paste a video link and run. - Built-in resilience & retry logic to improve success on slower connections. - Leverages Apify platform advantages: scheduling, webhooks, dataset exports (JSON, CSV, Excel), API, and proxy rotation. ### Example results You can browse sample run results here: ``` summaryUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/summary.txt transcriptJsonUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/transcript.json transcriptTxtUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/transcript.txt transcriptSrtUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/transcript.srt transcriptVttUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/transcript.vtt transcriptTsvUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/transcript.tsv transcriptJsonCompactUrl: https://api.apify.com/v2/key-value-stores/YlZlBDpzfNNXGrv5D/records/transcript.writer.json ``` ### What data can this Actor extract? The Actor produces: 1. A dataset record (one item per run / video) containing core metadata and convenience fields. 2. Multiple transcript artifacts stored in the default Key‑Value Store (structured JSON, writer JSON, TXT, SRT, VTT, TSV, optional summary). #### Dataset Record / Output Fields (canonical) | Field | Description | Example | |-------|-------------|---------| | url | Original YouTube video URL | `https://www.youtube.com/watch?v=CiREU-RAlf8` | | videoId | YouTube video ID | `CiREU-RAlf8` | | title | Video title | `How Does Ageing Impact Muscle Growth and Strength? Ft. Lyle McDonald` | | durationSeconds | Video duration in seconds | `503.037125` | | language | Detected language code | `en` | | segmentCount | Number of transcript segments | `76` | | generated_formats | List of generated transcript format short codes | `["txt","vtt","srt","tsv","json"]` | | transcriptKey | KV store key for structured transcript JSON | `transcript.json` | | resultsDataset | Dataset ID containing transcript segments | `9hP3aeAjoamHrYxFa` | | resultsDatasetUrl | API URL to fetch dataset items as JSON | `https://api.apify.com/v2/datasets//items?format=json` | | transcriptJsonUrl | Structured transcript (`transcript.json`) | `.../transcript.json` | | transcriptJsonCompactUrl | Compact writer JSON (`transcript.writer.json`) | `.../transcript.writer.json` | | transcriptTxtUrl | Plain text transcript (`transcript.txt`) | `.../transcript.txt` | | transcriptSrtUrl | SubRip subtitles (`transcript.srt`) | `.../transcript.srt` | | transcriptVttUrl | WebVTT subtitles (`transcript.vtt`) | `.../transcript.vtt` | | transcriptTsvUrl | Tab-separated timings (`transcript.tsv`) | `.../transcript.tsv` | | summaryUrl | AI-generated summary (`summary.txt`) | `.../summary.txt` | | formatUrls | Map of format code -> direct URL (includes `structured`, `json`, `summary`) | `{ "txt": "...", "structured": "..." }` | Structured transcript (`transcript.json`) contains full segment objects (start, end, text). Writer JSON (`transcript.writer.json`) is a compact variant optimized for certain downstream tooling. Subtitles (SRT/VTT) contain timed caption blocks; TSV contains per-segment timings (start/end ms) and text. #### Output Example (Actor Output Object) ```json { "videoId": "CiREU-RAlf8", "language": "en", "segmentCount": 76, "durationSeconds": 503.037125, "transcriptKey": "transcript.json", "resultsDataset": "9hP3aeAjoamHrYxFa", "resultsDatasetUrl": "https://api.apify.com/v2/datasets/9hP3aeAjoamHrYxFa/items?format=json", "transcriptJsonUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.json", "transcriptTxtUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.txt", "transcriptSrtUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.srt", "transcriptVttUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.vtt", "transcriptTsvUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.tsv", "transcriptJsonCompactUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.writer.json", "summaryUrl": "https://api.apify.com/v2/key-value-stores//records/summary.txt", "formatUrls": { "txt": "https://api.apify.com/v2/key-value-stores//records/transcript.txt", "vtt": "https://api.apify.com/v2/key-value-stores//records/transcript.vtt", "srt": "https://api.apify.com/v2/key-value-stores//records/transcript.srt", "tsv": "https://api.apify.com/v2/key-value-stores//records/transcript.tsv", "json": "https://api.apify.com/v2/key-value-stores//records/transcript.writer.json", "structured": "https://api.apify.com/v2/key-value-stores//records/transcript.json", "summary": "https://api.apify.com/v2/key-value-stores//records/summary.txt" } } ``` #### Sample Dataset Record ```json { "url": "https://www.youtube.com/watch?v=CiREU-RAlf8", "videoId": "CiREU-RAlf8", "title": "How Does Ageing Impact Muscle Growth and Strength? Ft. Lyle McDonald", "durationSeconds": 503.037125, "language": "en", "segmentCount": 76, "generated_formats": ["txt","vtt","srt","tsv","json"], "transcriptKey": "transcript.json", "resultsDataset": "9hP3aeAjoamHrYxFa", "resultsDatasetUrl": "https://api.apify.com/v2/datasets/9hP3aeAjoamHrYxFa/items?format=json", "transcriptJsonUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.json", "transcriptTxtUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.txt", "transcriptSrtUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.srt", "transcriptVttUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.vtt", "transcriptTsvUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.tsv", "transcriptJsonCompactUrl": "https://api.apify.com/v2/key-value-stores//records/transcript.writer.json", "summaryUrl": "https://api.apify.com/v2/key-value-stores//records/summary.txt", "formatUrls": { "txt": "https://api.apify.com/v2/key-value-stores//records/transcript.txt", "vtt": "https://api.apify.com/v2/key-value-stores//records/transcript.vtt", "srt": "https://api.apify.com/v2/key-value-stores//records/transcript.srt", "tsv": "https://api.apify.com/v2/key-value-stores//records/transcript.tsv", "json": "https://api.apify.com/v2/key-value-stores//records/transcript.writer.json", "structured": "https://api.apify.com/v2/key-value-stores//records/transcript.json", "summary": "https://api.apify.com/v2/key-value-stores//records/summary.txt" } } ``` ### Pricing & Run Expectations This Actor is optimized to be predictable and transparent. If your Apify account uses Pay‑Per‑Event pricing the following usage events are charged: | Event name | When it happens | How the count is calculated | |------------|-----------------|-----------------------------| | run-start | As soon as a run begins (after input validation) | Always 1 per run | | transcription-minute | After successful transcription | Ceil(video duration seconds / 60) | | summary-token | After AI summary generation (only if summary enabled) | Total AI model tokens used for the summary | #### Practical examples | Video length | Minutes charged | Summary enabled? | Total Cost | |--------------|-----------------|------------------|-------------------------------------| | 62 seconds | 2 | No | $0.001 + $0.05 = $0.051 | | 8m 23s | 9 | Yes | $0.001 + $0.45 + $0.114 = $0.565 | | 42m 00s | 42 | No | $0.001 + $2.1 = $2.101 | ### Tips & Best Practices - Provide clean, single video URLs (avoid playlists unless specifying a single item link). - If language detection occasionally misclassifies, supply the explicit language code. - Use dataset exports for bulk text analytics (e.g., sentiment, topic clustering) downstream. - Subtitle files (SRT/VTT) can be imported directly into most video editors or LMS platforms. - Schedule runs for recurring channels once playlist/batch mode becomes available (see future improvements). ### Future Improvements Planned enhancements (excluding already delivered AI summaries): - Playlist / batch input (process multiple URLs in one run) - Speaker diarization (label speakers in transcripts) - Sentiment & topic tagging enrichment - Configurable output format selection (generate only needed files) - More advanced summary styles (bullets, Q\&A, multi-length abstraction) ### FAQ **Is it legal to transcribe YouTube videos?**\ Public videos can generally be processed for personal or analytical use. Respect copyright and platform terms. Avoid redistributing transcripts if not permitted. **Can I process private or region-locked videos?**\ Only publicly accessible URLs that play from the environment can be handled. **Do I need to specify the language?**\ No—automatic detection runs by default. Provide a language code if consistency is critical. **Are AI summaries supported now?**\ Yes. **Why is my runtime slower on very long videos?**\ Runtime scales with total audio duration. Network variability and video encoding also affect speed. **Can I integrate this with other tools?**\ Yes—use the Apify API, webhooks, or Zapier/Make integrations to trigger downstream processing. **Does it summarize live streams?**\ Currently focused on completed videos. Live/ongoing stream support is not yet available. ### Disclaimer & Ethical Use Results may include personal statements spoken by creators. Avoid extracting or publishing sensitive information without consent. Ensure usage aligns with local regulations and YouTube Terms of Service. If in doubt, consult legal counsel. > Our solution extracts only publicly available speech content. Personal data protections (e.g. GDPR) may still apply; evaluate lawful basis before large-scale processing. ### Support & Feedback Encounter an issue or need a custom enhancement (e.g., AI summaries, batch playlists)? Open an issue, leave a comment on the Actor page, or reach out via Apify support. Feedback helps prioritize future improvements. ### Use Cases Recap - Rapid video content triage for editors & journalists - Study aids and note generation for educational channels - Caption preparation and adaptation - Research aggregation across thematic videos - Accessibility enhancement (text alternatives) Leverage Apify scheduling + API to build automated video intelligence pipelines with transcript search, preview summaries, and downstream analytics. # Actor input Schema ## `url` (type: `string`): A full URL to a public YouTube video (e.g. https://www.youtube.com/watch?v=dQw4w9WgXcQ) ## `language` (type: `string`): Optional language code (e.g. en, es) to force whisper transcription language; if omitted it will auto-detect. ## `enable_summary` (type: `boolean`): Generate an AI-powered summary of the transcript. ## Actor input object example ```json { "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ", "language": "", "enable_summary": true } ``` # 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 '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" }; // Run the Actor and wait for it to finish const run = await client.actor("automify/yt-ai-summarizer").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 '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" } # Run the Actor and wait for it to finish run = client.actor("automify/yt-ai-summarizer").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 '{ "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" }' | apify call automify/yt-ai-summarizer --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,automify/yt-ai-summarizer" } } } ``` 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 ` 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/1oCG6D3yQr7N4VHl0/builds/zJlhi04Rq6RpaGqcB/openapi.json