# Instagram Transcript Scraper (`automly/instagram-transcript-scraper`) Actor Turn Instagram reels into text: get the full transcript with timestamps and the spoken language for every reel of any public profile or reel link, plus caption, likes, comments and length. Bulk profiles, date filter. No login. - **URL**: https://apify.com/automly/instagram-transcript-scraper.md - **Developed by:** [Automly](https://apify.com/automly) (community) - **Categories:** Social media, Videos - **Features:** Limited permissions - **Stats:** 16 total users, 4 monthly users, 95.5% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $2.50 / 1,000 transcripts This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. 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 ## Instagram Transcript Scraper ### What is Instagram Transcript Scraper? **Instagram Transcript Scraper** turns **Instagram reels into text**. Paste usernames, profile links or reel links, click **Start**, and get one row per reel with **everything that was said in it**: the full transcript, the transcript in timed parts (start and end second of each sentence) and the spoken language, next to the reel's caption, length, likes, comment count and posting time. Download it as Excel, CSV or JSON, or schedule it to transcribe new reels every day. - 🗣️ **Full transcripts:** every word spoken in the reel, as one text and in timed parts - 🌍 **Many languages:** the spoken language is detected for each reel: English, Spanish, Portuguese, French and more - 👤 **Whole profiles or single reels:** the latest reels of any public profile, or any reel by its link - 🎵 **Music-only reels are free:** a reel with no speech is saved and marked, and you are not charged for it - 🔓 **No login:** no Instagram account, cookies or API key needed - 💸 **Pay per transcript:** you pay only for the reels that have speech ### What can Instagram Transcript Scraper do? - Transcribe the **latest reels of many profiles** in one run, up to the number you choose per profile - Transcribe **single reels** from their links - Find out **what creators say**, not just what they write in the caption - Get **timed transcripts** to make subtitles, clips or quotes - Keep only reels **posted after a date**, or skip **pinned reels** - Export to Excel, CSV, JSON, HTML or XML, or send the results to Google Sheets, Make, Zapier and more ### What data can you get from Instagram reels? | | | | |---|---|---| | 🗣️ Transcript | ⏱️ Timed transcript parts | 🌍 Spoken language | | 🎬 Reel URL and ID | ✍️ Caption | #️⃣ Hashtags and 📢 mentions | | ⏱️ Length in seconds | ❤️ Likes | 💬 Comments count | | 📹 Video URL | 🎧 Audio track URL | 🖼️ Cover image | | 🎵 Music: artist, song, original audio | 👤 Owner username, name, ID, verified | 🕒 Posted time | ### How to get the transcript of Instagram reels 1. [Create a free Apify account](https://console.apify.com/sign-up) (no credit card needed). 2. Open **Instagram Transcript Scraper**. 3. Paste one or more **usernames, profile links or reel links**, one per line. 4. Choose how many **reels per profile** you want transcribed. 5. Click **Start**, then download the results as Excel, CSV, JSON, HTML or XML. ### How much does it cost to transcribe Instagram reels? You pay per reel with speech. The transcript price includes the first 3 minutes of each reel; a longer reel also pays an **extra minute** for every started minute past the third. Higher Apify plans pay less: | Apify plan | Per 1,000 transcripts | Per 1,000 extra minutes | |---|---|---| | Free | $4.50 | $1.50 | | Starter (Bronze) | $4.00 | $1.25 | | Scale (Silver) | $3.50 | $1.00 | | Business (Gold) and higher | $2.50 | $1.00 | So a 5-minute reel is 1 transcript and 2 extra minutes. Platform usage is included in these prices, so you pay nothing else for the run. There is no start fee. Example: 1,000 one-minute reels cost $4.00 on Starter, $3.50 on Scale and $2.50 on Business and higher. Never charged: - reels with no speech (music only or silence) and reels with no sound, - photo posts, private profiles, and usernames or links that do not exist, - reels whose sound could not be downloaded or transcribed, - extra minutes of any reel that a Free plan run cut to its first minute, and reels the run reached after its free minute was used. Every Apify account gets **$5 of free usage each month**. **On the Apify Free plan**, transcripts made from the audio use a lighter, slower method, so expect lower accuracy (more wrong words, most of all in songs and noisy reels), and a run transcribes up to 1 minute of audio: a longer reel gets its first minute, and reels past that minute are saved as not transcribed and are not charged. Keep the default 1 GB memory: with less, a Free plan run transcribes no audio. Paid Apify plans get full-accuracy transcripts with no such limit. ### ⬇️ Input Each line can be a username (`hubermanlab`), `@hubermanlab`, a profile link (`https://www.instagram.com/natgeo/` or `https://www.instagram.com/natgeo/reels/`), a profile ID (`787132`) or a reel link (`https://www.instagram.com/reel/DeTUk4sDSp-/`). Mix them freely. | Setting | What it does | |---|---| | Usernames, profile links or reel links | What to transcribe, one per line | | Reels per profile | The most reels to transcribe from each profile, newest first (default 10) | | Only reels newer than | A date like `2026-09-01` or an age like `7 days`, `2 weeks`, `3 months` | | Skip pinned reels | Leave out the reels a profile pinned to the top of its grid | | Spoken language (optional) | A two-letter code such as `en` or `es` when every reel is in that language. Leave empty to detect each reel's language | Example: ```json { "username": ["hubermanlab", "https://www.instagram.com/nasa/", "https://www.instagram.com/reel/DeTUk4sDSp-/"], "resultsLimit": 10, "onlyPostsNewerThan": "30 days", "skipPinnedPosts": false } ``` The input uses the same field names as popular Instagram reel scrapers, so you can switch without changing your integration. ### ⬆️ Output You get one row per reel. View them as a table in Apify Console or download them as Excel, CSV, JSON, HTML or XML. ```json { "inputUrl": "https://www.instagram.com/reel/DeuH0dDFGcg/", "id": "4012178708962240288", "type": "Video", "shortCode": "DeuH0dDFGcg", "caption": "There's a lot of ground to cover when you're building a Moon Base.\n\nWe're sharing the latest details on the vehicles that will help pave the way for an enduring human presence near the lunar South Pole. Check @NASA's link-in-bio for the full update.", "hashtags": [], "mentions": ["NASA"], "url": "https://www.instagram.com/reel/DeuH0dDFGcg/", "commentsCount": 491, "dimensionsHeight": 1280, "dimensionsWidth": 720, "displayUrl": "https://scontent-sea5-1.cdninstagram.com/v/t51.82787-15/858994525_18660374401049152_3463301113379866293_n.jpg", "videoUrl": "https://scontent-sea5-1.cdninstagram.com/o1/v/t2/f2/m86/AQNVoUntep4zsMecgTtfYBkHyodFVbezkELNXy5WMP-TsL8XUSP3r22EGSJURxYSlLN5tyEf_xXPHDG_Rne9PpLgWqPYwgjGHVa-Wss.mp4", "audioUrl": "https://scontent-sea5-1.cdninstagram.com/o1/v/t2/f2/m78/AQOSyXh1xgEZyBBV4XxQw7D8Tqc_QMrP_Kt8kBw-E2-5Rd8u5g0QHsCxMfYCkaM1mj3mEgaNKKgT1IQzogifYzJXpRs_FqJNrSoLpq4.mp4", "alt": null, "likesCount": 62100, "likesHidden": false, "videoDuration": 45.824, "timestamp": "2026-10-20T15:10:43Z", "ownerFullName": "NASA", "ownerUsername": "nasa", "ownerId": "528817151", "ownerVerified": true, "isPinned": false, "productType": "clips", "paidPartnership": false, "sponsors": [], "taggedUsers": [{"id": "1104426670", "username": "nasaartemis", "full_name": "NASA Artemis", "is_verified": true, "profile_pic_url": "https://scontent-sea5-1.cdninstagram.com/v/t51.82787-19/670016304_n.jpg"}], "coauthorProducers": [{"id": "1104426670", "username": "nasaartemis", "full_name": "NASA Artemis", "is_verified": true, "profile_pic_url": "https://scontent-sea5-1.cdninstagram.com/v/t51.82787-19/670016304_n.jpg"}], "musicInfo": {"artist_name": "nasa", "song_name": "Original audio", "uses_original_audio": true, "should_mute_audio": false, "audio_id": "29906171498985608"}, "locationName": null, "locationId": null, "isCommentsDisabled": false, "transcriptStatus": "transcribed", "transcriptLanguage": "en", "transcript": "Think about hundreds of square miles where we have different assets. Definitely mobility systems. There's a lot of people spend a lot of time making sure every detail is right and it's really specific to the job it needs to do. Viper very much acts as a scout for Moonbase. We've already ticked through a couple of important milestones. We've already built three mockups, actually two of them within three weeks. This is really about going to stay to learn how to live on the Moon. There are a lot of steps that has to launch. We have to land, but I'm certainly most interested in seeing the rover explore and understand all the secrets about the South Pole of the Moon. Our goal is to enable humans to be operating on the surface of the Moon on a permanent basis.", "transcriptSegments": [{"start": 0.08, "end": 7.08, "text": "Think about hundreds of square miles where we have different assets. Definitely mobility systems."}, {"start": 7.08, "end": 14.08, "text": "There's a lot of people spend a lot of time making sure every detail is right and it's really specific to the job it needs to do."}], "fetchedAt": "2026-11-01T00:46:24Z" } ``` `transcriptStatus` tells you what happened with each reel: | Status | Meaning | Charged | |---|---|---| | `transcribed` | Speech (or sung words) was found; `transcript` has it | Yes | | `no_speech` | Instrumental music, sounds or silence only; `transcript` is empty | No | | `no_audio` | The reel has no sound, or the link is a photo post (`not_a_video`) | No | | `audio_unavailable` | The reel's sound could not be read this time; run it again later | No | Instagram media links (`videoUrl`, `audioUrl`, `displayUrl`) expire after a few days, so download the files you need soon after the run. Each run also saves a short report: how many reels had speech, and any username or link that does not exist. ### How can I use Instagram reel transcripts? - **Content research:** read what top creators in your niche actually say, hook by hook - **Repurposing:** turn your own reels into blog posts, newsletters, captions and subtitles - **Brand monitoring:** find reels that mention your brand or product out loud, not only in the caption - **Search and analysis:** load transcripts into spreadsheets, databases or search tools to compare creators and topics - **Influencer vetting:** check what a creator talks about before you work with them ### Use it from your code Run the actor from your own code with the [Apify API](https://docs.apify.com/api/v2) or the Python and JavaScript clients: ```python from apify_client import ApifyClient client = ApifyClient("") run = client.actor("automly/instagram-transcript-scraper").call(run_input={ "username": ["hubermanlab", "nasa"], "resultsLimit": 10, }) for reel in client.dataset(run["defaultDatasetId"]).iterate_items(): print(reel["url"], reel["transcriptLanguage"], reel["transcript"]) ``` ### 🤖 Use with assistants and agents (MCP) Connect any MCP-compatible assistant or agent to the Apify MCP server at https://mcp.apify.com (sign in with your Apify account), and it can find this actor, fill in the input and read the results by itself. Ask in plain words, for example *"Get the transcripts of the last 10 reels of hubermanlab"*, and the agent runs `automly/instagram-transcript-scraper` with an input like `{"username": ["hubermanlab"], "resultsLimit": 10}`. Agent runs cost the same as runs you start yourself. ### ❓FAQ #### How accurate are the transcripts? Clear speech in the main languages comes out close to word for word. Accuracy drops with loud background music, several people talking at once, strong accents and rare languages. If all your reels are in one language, set **Spoken language** to its code (for example `es`) for the best result. #### Which languages are supported? The spoken language is detected for each reel, and the transcript is in that language (it is not translated). English, Spanish, Portuguese and French come out best; other common languages work too, with more mistakes in less common ones. #### Is the transcript the same as the caption? No. The caption is the text the creator wrote under the reel. The transcript is what is said in the reel's audio. You get both. #### What happens with music-only reels? Reels with only instrumental music, sound effects or silence are saved with `transcriptStatus` set to `no_speech` and an empty transcript, and you are not charged for them. Words sung in a song are transcribed like speech. #### How many reels can I transcribe from one profile? As many as the profile shows on its grid. Set **Reels per profile** to the number you want; the newest come first, after any pinned reels. #### How long does it take? Most reels are transcribed in a few seconds each, and several reels are transcribed at the same time. Long reels take longer. #### Does it work for private accounts? No. Reels of private accounts are not public. A private profile is listed in the run's report as not available, and you are not charged for it. #### What happens with a username or link that does not exist? It is skipped and listed in the run's report as not found. The run still finishes successfully and you are not charged for it. #### Do I need an Instagram account? No. You don't need an Instagram account, cookies or an API key. #### Can I connect Instagram Transcript Scraper to other tools? Yes. Start runs and download results with the Apify API or the Python and JavaScript clients, send results to Make, Zapier, n8n, Google Sheets or Slack with Apify integrations and webhooks, or let agents run it through the Apify MCP server at [mcp.apify.com](https://mcp.apify.com). #### Is it legal to transcribe Instagram reels? This tool only processes reels that people chose to show publicly. It does not collect private data such as email addresses or phone numbers. Reels and their transcripts can still contain personal data, which may be protected by laws such as GDPR, and reels are protected by copyright, so use the transcripts for a legitimate reason such as research, and ask a lawyer if you are unsure. You can read more in [Is web scraping legal?](https://blog.apify.com/is-web-scraping-legal/) Instagram Transcript Scraper is an independent tool. It is not affiliated with, endorsed by or sponsored by Instagram or Meta. #### Something isn't working. What should I do? Open the **Issues** tab and tell us the username or link and what you expected. We usually reply within a day. ### Scrape more Instagram data | Actor | What you get | |---|---| | [Instagram Comments Scraper](https://apify.com/automly/instagram-comments-scraper) | Every comment on a post or reel, newest first | | [Instagram Posts & Reels Scraper](https://apify.com/automly/instagram-profile-posts-scraper) | A profile's posts and reels together, plus its profile info | | [Instagram Profile Scraper](https://apify.com/automly/instagram-profile-data-scraper) | Full profiles: bio, every bio link, exact post count, highlights | ### ⭐ Your feedback Ideas, missing fields or problems: open the **Issues** tab and we'll take a look. If Instagram Transcript Scraper saved you time, a short review on the **Reviews** tab helps other people find it. # Actor input Schema ## `username` (type: `array`): Instagram usernames, profile links, profile IDs or reel links, one per line, e.g. hubermanlab, https://www.instagram.com/natgeo/ or https://www.instagram.com/reel/DeTUk4sDSp-/. Each profile gives its latest reels; each reel link gives that reel. ## `resultsLimit` (type: `integer`): The most reels to transcribe from each profile, newest first (pinned reels come first, as on Instagram), e.g. 10. Not used for reel links. ## `onlyPostsNewerThan` (type: `string`): Skip older reels: a date like 2026-09-01 (UTC) or an age like 7 days, 2 weeks or 3 months. Leave empty for no date limit. Not used for reel links. ## `skipPinnedPosts` (type: `boolean`): Leave out the reels a profile pinned to the top of its grid. ## `language` (type: `string`): A two-letter language code such as en, es, pt, fr, de or hi when all the reels are in that language, e.g. es. Leave empty to detect the language of each reel. ## `proxyConfiguration` (type: `object`): Proxy settings. The default works for most runs. ## Actor input object example ```json { "username": [ "hubermanlab" ], "resultsLimit": 3, "skipPinnedPosts": false, "proxyConfiguration": { "useApifyProxy": true } } ``` # Actor output Schema ## `overview` (type: `string`): No description ## `results` (type: `string`): No description ## `report` (type: `string`): No description # 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 = { "username": [ "hubermanlab" ], "resultsLimit": 3, "proxyConfiguration": { "useApifyProxy": true } }; // Run the Actor and wait for it to finish const run = await client.actor("automly/instagram-transcript-scraper").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 = { "username": ["hubermanlab"], "resultsLimit": 3, "proxyConfiguration": { "useApifyProxy": True }, } # Run the Actor and wait for it to finish run = client.actor("automly/instagram-transcript-scraper").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 '{ "username": [ "hubermanlab" ], "resultsLimit": 3, "proxyConfiguration": { "useApifyProxy": true } }' | apify call automly/instagram-transcript-scraper --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,automly/instagram-transcript-scraper" } } } ``` 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/v3z7yPE65x5kIXYzB/builds/YLKZnXdQv4zs5Q7xw/openapi.json