# Instagram Ai Transcript Extractora (`scrapers-hub/instagram-ai-transcript-extractor`) Actor 🎥 Instagram AI Transcript Extractor pulls accurate transcripts from Reels, posts & Lives in seconds. 🤖 Auto timestamps, speaker tags & multilingual captions. 📄 Export SRT, VTT, TXT or CSV. 🚀 Perfect for creators, marketers & researchers—repurpose, subtitle & boost SEO. - **URL**: https://apify.com/scrapers-hub/instagram-ai-transcript-extractor.md - **Developed by:** [Scrapers Hub](https://apify.com/scrapers-hub) (community) - **Categories:** Social media, Automation, Other - **Stats:** 4 total users, 3 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $1.99 / 1,000 results This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. 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. Actors are written with capital "A". ## 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. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ### 🎙️ Instagram AI Transcript Extractor: Ultimate Speech-to-Text Intelligence Transform Instagram videos and entire channels into structured, word-perfect text data. This tool uses cutting-edge AI to extract transcripts with 99.4% accuracy, providing precise timestamps for every single word. No more manual transcribing—just paste a link or a username and get instant results. #### ✨ Revolutionary Features 🔤 Word-Level Precision: Get exact timestamps for every individual word. Perfect for professional subtitling and deep linguistic analysis. 🆕 Automatic Channel Scraping: Simply enter a username to extract transcripts from their entire catalog of Reels. No need to collect URLs manually. ⚡ Lightning Fast Processing: Choose "Fast Mode" to boost extraction speeds by 50% for high-volume workflows. 📊 Comprehensive Metadata: Alongside transcripts, get 30+ data points including likes, views, comments, music info, and owner details. 🗓️ Smart Date Filtering: Scrape content only from a specific timeframe (e.g., "last 30 days") to stay updated with the latest trends. 🔒 Privacy First: Works entirely on public data. No login, cookies, or account access required. #### input ```json INPUT_CONFIG = { "instagramUrl": "https://www.instagram.com/reel/DSifsQtAQXx/", "wordLevelTimestamps": True, "fastProcessing": False } ```` #### 📤 Professional Data Output The extractor provides a rich JSON response. Below is a snapshot of the core fields: ```json [ { "transcript": "Now addressing violence is extremely complex, but just as we no longer rely on hospitals and emergency rooms alone to improve public health, we cannot rely on the justice system alone to create safety. In 2014, I got a call from my friend, Raspor Raka, a mayor of Newark, New Jersey. Mayor Baraka asked me to help him to strengthen his community violence intervention strategy. With the modest investment from local philanthropies, I launched a Newark Community Street team. I hired 16 credible messengers, many of them ex-game members and formerly incarcerated folks who have deep relationships in the neighborhood, retrained them in conflict resolution and mediation strategies, and deployed them in high violence areas, and asked them to use their relationship capital to intervene and mediate game disputes that could lead to violence. When we started out working in Newark in 2014, the city had 103 homicides. In 2024, we had 37. And I'm found these are not just numbers, they're actual lives saved, but very few essential community organizations have the know how to become a permanent part of the city's public safety workforce. In 2021, I launched the community-based public safety collective to spread the Newark Community Street team strategy nationwide. We've already helped 150 organizations in 60 plus cities. But what I've come to understand is that, peace is a journey and not a destination. And that public safety is not just the absence of violence and crime, but the presence of well-being in the infrastructure to support victims and survivors in their healing journey.", "segments": [ { "text": "Now addressing violence is extremely complex,", "start": 0.0, "end": 2.28 }, { "text": "but just as we no longer rely on hospitals", "start": 2.82, "end": 5.78 }, { "text": "and emergency rooms alone to improve public health,", "start": 5.78, "end": 9.0 }, { "text": "we cannot rely on the justice system alone to create safety.", "start": 9.98, "end": 13.7 }, { "text": "In 2014, I got a call from my friend,", "start": 14.18, "end": 19.56 }, { "text": "Raspor Raka, a mayor of Newark, New Jersey.", "start": 19.68, "end": 21.4 }, { "text": "Mayor Baraka asked me to help him to strengthen", "start": 22.04, "end": 23.96 }, { "text": "his community violence intervention strategy.", "start": 23.96, "end": 25.88 }, { "text": "With the modest investment from local philanthropies,", "start": 26.46, "end": 29.04 }, { "text": "I launched a Newark Community Street team.", "start": 29.04, "end": 30.96 }, { "text": "I hired 16 credible messengers,", "start": 31.4, "end": 33.9 }, { "text": "many of them ex-game members", "start": 34.76, "end": 36.24 }, { "text": "and formerly incarcerated folks", "start": 36.24, "end": 37.68 }, { "text": "who have deep relationships in the neighborhood,", "start": 37.68, "end": 39.74 }, { "text": "retrained them in conflict resolution", "start": 40.46, "end": 41.98 }, { "text": "and mediation strategies,", "start": 41.98, "end": 43.24 }, { "text": "and deployed them in high violence areas,", "start": 43.88, "end": 45.62 }, { "text": "and asked them to use their relationship capital", "start": 45.98, "end": 48.7 }, { "text": "to intervene and mediate game disputes", "start": 48.7, "end": 50.96 }, { "text": "that could lead to violence.", "start": 50.96, "end": 51.98 }, { "text": "When we started out working in Newark in 2014,", "start": 52.78, "end": 55.02 }, { "text": "the city had 103 homicides.", "start": 55.82, "end": 57.96 }, { "text": "In 2024, we had 37.", "start": 58.68, "end": 60.78 }, { "text": "And I'm found these are not just numbers,", "start": 62.3, "end": 64.78 }, { "text": "they're actual lives saved,", "start": 64.78, "end": 66.3 }, { "text": "but very few essential community organizations", "start": 66.88, "end": 69.16 }, { "text": "have the know how to become a permanent part", "start": 69.16, "end": 71.4 }, { "text": "of the city's public safety workforce.", "start": 71.4, "end": 72.94 }, { "text": "In 2021, I launched the community-based", "start": 73.58, "end": 76.0 }, { "text": "public safety collective to spread the Newark Community", "start": 76.0, "end": 78.82 }, { "text": "Street team strategy nationwide.", "start": 78.82, "end": 80.62 }, { "text": "We've already helped 150 organizations in 60 plus cities.", "start": 81.16, "end": 84.56 }, { "text": "But what I've come to understand is that,", "start": 85.14, "end": 87.36 }, { "text": "peace is a journey and not a destination.", "start": 87.36, "end": 89.54 }, { "text": "And that public safety is not just the absence", "start": 90.16, "end": 92.18 }, { "text": "of violence and crime,", "start": 92.18, "end": 93.18 }, { "text": "but the presence of well-being", "start": 93.64, "end": 94.94 }, { "text": "in the infrastructure to support victims", "start": 94.94, "end": 96.84 }, { "text": "and survivors in their healing journey.", "start": 96.84, "end": 98.26 } ], "words": [ { "word": "Now", "start": 0.0, "end": 0.1 }, { "word": "addressing", "start": 0.1, "end": 0.5 }, { "word": "violence", "start": 0.5, "end": 0.88 }, { "word": "is", "start": 0.88, "end": 1.08 }, { "word": "extremely", "start": 1.08, "end": 1.58 }, { "word": "complex,", "start": 1.58, "end": 2.28 }, { "word": "but", "start": 2.82, "end": 3.22 }, { "word": "just", "start": 3.22, "end": 3.42 }, { "word": "as", "start": 3.42, "end": 3.64 }, { "word": "we", "start": 3.64, "end": 3.8 }, { "word": "no", "start": 3.8, "end": 4.04 }, { "word": "longer", "start": 4.04, "end": 4.4 }, { "word": "rely", "start": 4.4, "end": 4.78 }, { "word": "on", "start": 4.78, "end": 5.2 }, { "word": "hospitals", "start": 5.2, "end": 5.78 }, { "word": "and", "start": 5.78, "end": 6.0 }, { "word": "emergency", "start": 6.0, "end": 6.36 }, { "word": "rooms", "start": 6.36, "end": 6.72 }, { "word": "alone", "start": 6.72, "end": 7.16 }, { "word": "to", "start": 7.16, "end": 7.98 }, { "word": "improve", "start": 7.98, "end": 8.3 }, { "word": "public", "start": 8.3, "end": 8.64 }, { "word": "health,", "start": 8.64, "end": 9.0 }, { "word": "we", "start": 9.74, "end": 10.06 }, { "word": "cannot", "start": 10.06, "end": 10.42 }, { "word": "rely", "start": 10.42, "end": 10.88 }, { "word": "on", "start": 10.88, "end": 11.3 }, { "word": "the", "start": 11.3, "end": 11.42 }, { "word": "justice", "start": 11.42, "end": 11.8 }, { "word": "system", "start": 11.8, "end": 12.16 }, { "word": "alone", "start": 12.16, "end": 12.52 }, { "word": "to", "start": 12.52, "end": 12.96 }, { "word": "create", "start": 12.96, "end": 13.24 }, { "word": "safety.", "start": 13.24, "end": 13.7 }, { "word": "In", "start": 14.18, "end": 14.4 }, { "word": "2014,", "start": 14.4, "end": 15.16 }, { "word": "I", "start": 15.56, "end": 17.24 }, { "word": "got", "start": 17.24, "end": 18.58 }, { "word": "a", "start": 18.58, "end": 18.72 }, { "word": "call", "start": 18.72, "end": 18.92 }, { "word": "from", "start": 18.92, "end": 19.14 }, { "word": "my", "start": 19.14, "end": 19.3 }, { "word": "friend,", "start": 19.3, "end": 19.56 }, { "word": "Raspor", "start": 19.68, "end": 19.98 }, { "word": "Raka,", "start": 19.98, "end": 20.22 }, { "word": "a", "start": 20.42, "end": 20.42 }, { "word": "mayor", "start": 20.42, "end": 20.52 }, { "word": "of", "start": 20.52, "end": 20.66 }, { "word": "Newark,", "start": 20.66, "end": 20.88 }, { "word": "New", "start": 20.96, "end": 21.04 }, { "word": "Jersey.", "start": 21.04, "end": 21.4 }, { "word": "Mayor", "start": 22.04, "end": 22.16 }, { "word": "Baraka", "start": 22.16, "end": 22.48 }, { "word": "asked", "start": 22.48, "end": 22.8 }, { "word": "me", "start": 22.8, "end": 22.98 }, { "word": "to", "start": 22.98, "end": 23.1 }, { "word": "help", "start": 23.1, "end": 23.28 }, { "word": "him", "start": 23.28, "end": 23.5 }, { "word": "to", "start": 23.5, "end": 23.64 }, { "word": "strengthen", "start": 23.64, "end": 23.96 }, { "word": "his", "start": 23.96, "end": 24.2 }, { "word": "community", "start": 24.2, "end": 24.42 }, { "word": "violence", "start": 24.42, "end": 24.82 }, { "word": "intervention", "start": 24.82, "end": 25.24 }, { "word": "strategy.", "start": 25.24, "end": 25.88 }, { "word": "With", "start": 26.46, "end": 26.72 }, { "word": "the", "start": 26.72, "end": 26.84 }, { "word": "modest", "start": 26.84, "end": 27.04 }, { "word": "investment", "start": 27.04, "end": 27.56 }, { "word": "from", "start": 27.56, "end": 27.76 }, { "word": "local", "start": 27.76, "end": 28.12 }, { "word": "philanthropies,", "start": 28.12, "end": 29.04 }, { "word": "I", "start": 29.04, "end": 29.46 }, { "word": "launched", "start": 29.46, "end": 29.72 }, { "word": "a", "start": 29.72, "end": 29.84 }, { "word": "Newark", "start": 29.84, "end": 30.06 }, { "word": "Community", "start": 30.06, "end": 30.36 }, { "word": "Street", "start": 30.36, "end": 30.68 }, { "word": "team.", "start": 30.68, "end": 30.96 }, { "word": "I", "start": 31.4, "end": 31.48 }, { "word": "hired", "start": 31.48, "end": 31.88 }, { "word": "16", "start": 31.88, "end": 32.78 }, { "word": "credible", "start": 32.78, "end": 33.32 }, { "word": "messengers,", "start": 33.32, "end": 33.9 }, { "word": "many", "start": 34.76, "end": 35.0 }, { "word": "of", "start": 35.0, "end": 35.2 }, { "word": "them", "start": 35.2, "end": 35.36 }, { "word": "ex", "start": 35.36, "end": 35.74 }, { "word": "-game", "start": 35.74, "end": 35.9 }, { "word": "members", "start": 35.9, "end": 36.24 }, { "word": "and", "start": 36.24, "end": 36.42 }, { "word": "formerly", "start": 36.42, "end": 36.8 }, { "word": "incarcerated", "start": 36.8, "end": 37.32 }, { "word": "folks", "start": 37.32, "end": 37.68 }, { "word": "who", "start": 37.68, "end": 38.1 }, { "word": "have", "start": 38.1, "end": 38.26 }, { "word": "deep", "start": 38.26, "end": 38.44 }, { "word": "relationships", "start": 38.44, "end": 39.02 }, { "word": "in", "start": 39.02, "end": 39.3 }, { "word": "the", "start": 39.3, "end": 39.38 }, { "word": "neighborhood,", "start": 39.38, "end": 39.74 }, { "word": "retrained", "start": 40.46, "end": 40.78 }, { "word": "them", "start": 40.78, "end": 41.0 }, { "word": "in", "start": 41.0, "end": 41.08 }, { "word": "conflict", "start": 41.08, "end": 41.42 }, { "word": "resolution", "start": 41.42, "end": 41.98 }, { "word": "and", "start": 41.98, "end": 42.18 }, { "word": "mediation", "start": 42.18, "end": 42.6 }, { "word": "strategies,", "start": 42.6, "end": 43.24 }, { "word": "and", "start": 43.88, "end": 43.98 }, { "word": "deployed", "start": 43.98, "end": 44.28 }, { "word": "them", "start": 44.28, "end": 44.54 }, { "word": "in", "start": 44.54, "end": 44.68 }, { "word": "high", "start": 44.68, "end": 44.84 }, { "word": "violence", "start": 44.84, "end": 45.18 }, { "word": "areas,", "start": 45.18, "end": 45.62 }, { "word": "and", "start": 45.98, "end": 46.1 }, { "word": "asked", "start": 46.1, "end": 46.38 }, { "word": "them", "start": 46.38, "end": 46.6 }, { "word": "to", "start": 46.6, "end": 46.76 }, { "word": "use", "start": 46.76, "end": 47.18 }, { "word": "their", "start": 47.18, "end": 47.5 }, { "word": "relationship", "start": 47.5, "end": 47.94 }, { "word": "capital", "start": 47.94, "end": 48.7 }, { "word": "to", "start": 48.7, "end": 49.18 }, { "word": "intervene", "start": 49.18, "end": 49.52 }, { "word": "and", "start": 49.52, "end": 49.78 }, { "word": "mediate", "start": 49.78, "end": 50.26 }, { "word": "game", "start": 50.26, "end": 50.64 }, { "word": "disputes", "start": 50.64, "end": 50.96 }, { "word": "that", "start": 50.96, "end": 51.22 }, { "word": "could", "start": 51.22, "end": 51.36 }, { "word": "lead", "start": 51.36, "end": 51.5 }, { "word": "to", "start": 51.5, "end": 51.64 }, { "word": "violence.", "start": 51.64, "end": 51.98 }, { "word": "When", "start": 52.78, "end": 53.02 }, { "word": "we", "start": 53.02, "end": 53.12 }, { "word": "started", "start": 53.12, "end": 53.44 }, { "word": "out", "start": 53.44, "end": 53.62 }, { "word": "working", "start": 53.62, "end": 53.9 }, { "word": "in", "start": 53.9, "end": 54.02 }, { "word": "Newark", "start": 54.02, "end": 54.22 }, { "word": "in", "start": 54.22, "end": 54.42 }, { "word": "2014,", "start": 54.42, "end": 55.02 }, { "word": "the", "start": 55.82, "end": 56.3 }, { "word": "city", "start": 56.3, "end": 56.5 }, { "word": "had", "start": 56.5, "end": 56.7 }, { "word": "103", "start": 56.7, "end": 57.24 }, { "word": "homicides.", "start": 57.24, "end": 57.96 }, { "word": "In", "start": 58.4, "end": 58.72 }, { "word": "2024,", "start": 58.72, "end": 59.08 }, { "word": "we", "start": 59.88, "end": 60.08 }, { "word": "had", "start": 60.08, "end": 60.18 }, { "word": "37.", "start": 60.18, "end": 60.78 }, { "word": "And", "start": 62.3, "end": 62.52 }, { "word": "I'm", "start": 62.52, "end": 62.6 }, { "word": "found", "start": 62.6, "end": 62.74 }, { "word": "these", "start": 62.74, "end": 63.12 }, { "word": "are", "start": 63.12, "end": 63.84 }, { "word": "not", "start": 63.84, "end": 64.08 }, { "word": "just", "start": 64.08, "end": 64.44 }, { "word": "numbers,", "start": 64.44, "end": 64.78 }, { "word": "they're", "start": 64.78, "end": 65.04 }, { "word": "actual", "start": 65.04, "end": 65.4 }, { "word": "lives", "start": 65.4, "end": 65.8 }, { "word": "saved,", "start": 65.8, "end": 66.3 }, { "word": "but", "start": 66.88, "end": 67.08 }, { "word": "very", "start": 67.08, "end": 67.4 }, { "word": "few", "start": 67.4, "end": 67.6 }, { "word": "essential", "start": 67.6, "end": 67.94 }, { "word": "community", "start": 67.94, "end": 68.4 }, { "word": "organizations", "start": 68.4, "end": 69.16 }, { "word": "have", "start": 69.16, "end": 69.58 }, { "word": "the", "start": 69.58, "end": 69.72 }, { "word": "know", "start": 69.72, "end": 69.88 }, { "word": "how", "start": 69.88, "end": 70.1 }, { "word": "to", "start": 70.1, "end": 70.3 }, { "word": "become", "start": 70.3, "end": 70.54 }, { "word": "a", "start": 70.54, "end": 70.82 }, { "word": "permanent", "start": 70.82, "end": 71.12 }, { "word": "part", "start": 71.12, "end": 71.4 }, { "word": "of", "start": 71.4, "end": 71.54 }, { "word": "the", "start": 71.54, "end": 71.64 }, { "word": "city's", "start": 71.64, "end": 72.0 }, { "word": "public", "start": 72.0, "end": 72.2 }, { "word": "safety", "start": 72.2, "end": 72.5 }, { "word": "workforce.", "start": 72.5, "end": 72.94 }, { "word": "In", "start": 73.58, "end": 73.76 }, { "word": "2021,", "start": 73.76, "end": 74.38 }, { "word": "I", "start": 74.74, "end": 75.1 }, { "word": "launched", "start": 75.1, "end": 75.34 }, { "word": "the", "start": 75.34, "end": 75.48 }, { "word": "community", "start": 75.48, "end": 75.76 }, { "word": "-based", "start": 75.76, "end": 76.0 }, { "word": "public", "start": 76.0, "end": 76.28 }, { "word": "safety", "start": 76.28, "end": 76.68 }, { "word": "collective", "start": 76.68, "end": 77.18 }, { "word": "to", "start": 77.18, "end": 77.8 }, { "word": "spread", "start": 77.8, "end": 78.12 }, { "word": "the", "start": 78.12, "end": 78.34 }, { "word": "Newark", "start": 78.34, "end": 78.58 }, { "word": "Community", "start": 78.58, "end": 78.82 }, { "word": "Street", "start": 78.82, "end": 79.18 }, { "word": "team", "start": 79.18, "end": 79.5 }, { "word": "strategy", "start": 79.5, "end": 79.92 }, { "word": "nationwide.", "start": 79.92, "end": 80.62 }, { "word": "We've", "start": 81.16, "end": 81.56 }, { "word": "already", "start": 81.56, "end": 81.84 }, { "word": "helped", "start": 81.84, "end": 82.08 }, { "word": "150", "start": 82.08, "end": 82.6 }, { "word": "organizations", "start": 82.6, "end": 83.32 }, { "word": "in", "start": 83.32, "end": 83.66 }, { "word": "60", "start": 83.66, "end": 83.96 }, { "word": "plus", "start": 83.96, "end": 84.18 }, { "word": "cities.", "start": 84.18, "end": 84.56 }, { "word": "But", "start": 85.14, "end": 85.34 }, { "word": "what", "start": 85.34, "end": 85.42 }, { "word": "I've", "start": 85.42, "end": 85.58 }, { "word": "come", "start": 85.58, "end": 85.7 }, { "word": "to", "start": 85.7, "end": 85.86 }, { "word": "understand", "start": 85.86, "end": 86.3 }, { "word": "is", "start": 86.3, "end": 87.04 }, { "word": "that,", "start": 87.04, "end": 87.36 }, { "word": "peace", "start": 87.36, "end": 87.94 }, { "word": "is", "start": 87.94, "end": 88.1 }, { "word": "a", "start": 88.1, "end": 88.22 }, { "word": "journey", "start": 88.22, "end": 88.56 }, { "word": "and", "start": 88.56, "end": 88.72 }, { "word": "not", "start": 88.72, "end": 88.86 }, { "word": "a", "start": 88.86, "end": 88.98 }, { "word": "destination.", "start": 88.98, "end": 89.54 }, { "word": "And", "start": 90.16, "end": 90.48 }, { "word": "that", "start": 90.48, "end": 90.6 }, { "word": "public", "start": 90.6, "end": 90.88 }, { "word": "safety", "start": 90.88, "end": 91.28 }, { "word": "is", "start": 91.28, "end": 91.4 }, { "word": "not", "start": 91.4, "end": 91.54 }, { "word": "just", "start": 91.54, "end": 91.76 }, { "word": "the", "start": 91.76, "end": 91.92 }, { "word": "absence", "start": 91.92, "end": 92.18 }, { "word": "of", "start": 92.18, "end": 92.42 }, { "word": "violence", "start": 92.42, "end": 92.64 }, { "word": "and", "start": 92.64, "end": 92.86 }, { "word": "crime,", "start": 92.86, "end": 93.18 }, { "word": "but", "start": 93.64, "end": 93.82 }, { "word": "the", "start": 93.82, "end": 93.94 }, { "word": "presence", "start": 93.94, "end": 94.24 }, { "word": "of", "start": 94.24, "end": 94.48 }, { "word": "well", "start": 94.48, "end": 94.62 }, { "word": "-being", "start": 94.62, "end": 94.94 }, { "word": "in", "start": 94.94, "end": 95.22 }, { "word": "the", "start": 95.22, "end": 95.32 }, { "word": "infrastructure", "start": 95.32, "end": 95.82 }, { "word": "to", "start": 95.82, "end": 96.14 }, { "word": "support", "start": 96.14, "end": 96.5 }, { "word": "victims", "start": 96.5, "end": 96.84 }, { "word": "and", "start": 96.84, "end": 97.02 }, { "word": "survivors", "start": 97.02, "end": 97.42 }, { "word": "in", "start": 97.42, "end": 97.6 }, { "word": "their", "start": 97.6, "end": 97.72 }, { "word": "healing", "start": 97.72, "end": 97.92 }, { "word": "journey.", "start": 97.92, "end": 98.26 } ], "displayUrl": "https://instagram.fdac3-1.fna.fbcdn.net/v/t51.82787-15/584362175_18551039620054100_8478295082147534771_n.jpg?stp=dst-jpg_e15_tt6&_nc_cat=109&ig_cache_key=Mzc4ODQ1ODYyNTQxMjk2MTA5ODE4NTUxMDM5NjE0MDU0MTAw.3-ccb7-5&ccb=7-5&_nc_sid=58cdad&efg=eyJ2ZW5jb2RlX3RhZyI6InhwaWRzLjEzMjB4MjM0OC5zZHIuQzMifQ%3D%3D&_nc_ohc=3jpOof5hJrkQ7kNvwFhbJE5&_nc_oc=AdkDFCemlMUhMI2v13RHaWawkSsso2Ie5kYOc4OqIxOIiuV1M1m1-soN7dTHR47mxdA&_nc_ad=z-m&_nc_cid=1112&_nc_zt=23&_nc_ht=instagram.fdac3-1.fna&_nc_gid=rSp-UtaENBg1pZvwwm5Pww&oh=00_AfnSr8xwloe4Q4vjEFfmNdnrgOiE8UkFKB0_fAVfw9b4Jw&oe=694F27A1", "instagramUrl": "https://www.instagram.com/p/DSTTww2ARNK/", "caption": "Public safety is not just the absence of crime, it’s the presence of well-being and support, says urban peace activist @AqeelaSherrills. In his TED Talk, he shares his vision of community-led peace programs and how his initiative, Scaling Safety — backed by TED’s @TheAudaciousProject — is empowering local leaders to help reduce violence and create lasting change. “Peace is a journey and not a destination,” he says. Visit the link in our bio to hear more of Aqeela’s story and the impact he’s making across the US.", "hashtags": "", "ownerUsername": "TED Talks", "ownerFullName": "TED Talks", "likesCount": 887, "videoViewCount": 0, "videoPlayCount": 0, "commentsCount": 20, "videoDuration": 98.43299865722656, "timestamp": "2025-12-15T00:00:00.000Z", "shortCode": "DSTTww2ARNK", "musicArtist": "TED Talks", "musicSong": "Original audio", "usesOriginalAudio": true, "locationName": "", "mentions": "AqeelaSherrills, TheAudaciousProject", "firstComment": "", "id": "DSTTww2ARNK", "type": "Video", "productType": "clips", "isSponsored": false, "isCommentsDisabled": false, "dimensionsHeight": 2560, "dimensionsWidth": 1440, "processedAt": "2025-12-22T15:33:21.594008+00:00Z", "status": "success", "videoUrl": "https://instagram.fdac3-1.fna.fbcdn.net/o1/v/t16/f2/m261/AQPaRIYS0HGTIbWltc6Dz_PGE7ZUKuf7d1PD0sjEGP-ibF_0HHrpvca9PyfLzIMvm6m9wCx3BE5jJlKTA0NpSkfM3XY_Au8bBAtLdQ.mp4?_nc_cat=111&_nc_oc=AdkwbiMhPUj54UELl61EppYK4qLlACezXZOnQSnjtw43Cqr9E-qCKSCxBfZT2HdCRvs&_nc_sid=8bf8fe&_nc_ht=instagram.fdac3-1.fna.fbcdn.net&_nc_ohc=a_YSGxPjN6UQ7kNvwFI_dwb&efg=eyJ2ZW5jb2RlX3RhZyI6Inhwdl9wcm9ncmVzc2l2ZS5JTlNUQUdSQU0uQ0xJUFMuQzMuMTQ0MC5yZW11eF9zb3VyY2UiLCJ4cHZfYXNzZXRfaWQiOjExMzgzMTE3MjE4MDI4MDQsImFzc2V0X2FnZV9kYXlzIjo2LCJ2aV91c2VjYXNlX2lkIjoxMDgyNywiZHVyYXRpb25fcyI6OTgsInVybGdlbl9zb3VyY2UiOiJ3d3cifQ%3D%3D&ccb=17-1&_nc_gid=rSp-UtaENBg1pZvwwm5Pww&_nc_zt=28&oh=00_AfmCaFClifiK7gT6ytuO7ac90EzlwKn9M_11OrohM1Vkyg&oe=694B31F1" } ] ``` ### 🚀 How It Works (3 Simple Steps) Step 1: Select Your Mode Single URL: Best for quick analysis of one specific Reel or video. Bulk URLs: Paste a list of links to process multiple videos at once. Channel Mode: Enter a username (e.g., @creators\_name) to scrape their recent library. Step 2: Configure & Run Set your preferences—enable word-level timestamps for subtitling or toggle Fast Processing for bulk jobs. Hit Run and let the AI engine handle the rest. Step 3: Download & Analyze In about 30 seconds, your data is ready. Export as JSON, CSV, or Excel to feed your subtitles, content research, or automation pipelines. ### 💼 Use Cases 🎬 Professional Subtitling & Captioning Generate .srt or .vtt files with perfect synchronization using word-level timing. 📈 Viral Trend Analysis Analyze the scripts of top-performing videos to discover speech patterns, keywords, and hooks that drive millions of views. 🤖 Automated Content Pipelines Connect the API to tools like n8n, Zapier, or Make to automatically transcribe every new video posted by your favorite creators. 🔬 Market Research Perform deep competitive intelligence by transcribing entire video catalogs of competitors to understand their messaging strategy. ### ❓ FAQ Q: How accurate is the transcription? A: We achieve a 99.4% accuracy rate for clear speech. High-quality audio yields professional-grade results. Q: Can it process private accounts? A: No. To ensure ethical data practices, the tool only works with publicly accessible content. Q: Does it work if there is only music? A: The tool will extract all metadata (likes, views, etc.), but the transcript field will remain empty if no speech is detected. Q4: How does Channel Scrape mode work? A: It automatically scrolls through a user's profile, identifies videos with speech, and processes them from newest to oldest. # Actor input Schema ## `instagramUrl` (type: `string`): The URL of the Instagram reel/video to scrape. ## `wordLevelTimestamps` (type: `boolean`): Set to true to extract word-level timestamps, false for only segment-level timestamps. ## `fastProcessing` (type: `boolean`): Set to true for faster but less accurate transcription (uses tiny model if fallback), false for more accurate. ## `proxyConfiguration` (type: `object`): Select proxies to be used by your crawler. ## Actor input object example ```json { "instagramUrl": "https://www.instagram.com/reel/DSifsQtAQXx/", "wordLevelTimestamps": true, "fastProcessing": false, "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } ``` # 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 = { "instagramUrl": "https://www.instagram.com/reel/DSifsQtAQXx/", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }; // Run the Actor and wait for it to finish const run = await client.actor("scrapers-hub/instagram-ai-transcript-extractor").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 = { "instagramUrl": "https://www.instagram.com/reel/DSifsQtAQXx/", "proxyConfiguration": { "useApifyProxy": True, "apifyProxyGroups": ["RESIDENTIAL"], }, } # Run the Actor and wait for it to finish run = client.actor("scrapers-hub/instagram-ai-transcript-extractor").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "instagramUrl": "https://www.instagram.com/reel/DSifsQtAQXx/", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }' | apify call scrapers-hub/instagram-ai-transcript-extractor --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=scrapers-hub/instagram-ai-transcript-extractor", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Instagram Ai Transcript Extractora", "description": "🎥 Instagram AI Transcript Extractor pulls accurate transcripts from Reels, posts & Lives in seconds. 🤖 Auto timestamps, speaker tags & multilingual captions. 📄 Export SRT, VTT, TXT or CSV. 🚀 Perfect for creators, marketers & researchers—repurpose, subtitle & boost SEO.", "version": "1.0", "x-build-id": "HDt21VS2cDjW1FPc8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapers-hub~instagram-ai-transcript-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapers-hub-instagram-ai-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapers-hub~instagram-ai-transcript-extractor/runs": { "post": { "operationId": "runs-sync-scrapers-hub-instagram-ai-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapers-hub~instagram-ai-transcript-extractor/run-sync": { "post": { "operationId": "run-sync-scrapers-hub-instagram-ai-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "instagramUrl" ], "properties": { "instagramUrl": { "title": "Instagram URL", "type": "string", "description": "The URL of the Instagram reel/video to scrape." }, "wordLevelTimestamps": { "title": "Word Level Timestamps", "type": "boolean", "description": "Set to true to extract word-level timestamps, false for only segment-level timestamps.", "default": true }, "fastProcessing": { "title": "Fast Processing", "type": "boolean", "description": "Set to true for faster but less accurate transcription (uses tiny model if fallback), false for more accurate.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Select proxies to be used by your crawler.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```