# Instagram AI Transcript Extractor (`fetch_cat/instagram-ai-transcript-extractor`) Actor Transcribe public Instagram Reels and videos into speech text, available timestamped segments, and media metadata. Export per-URL results as JSON or CSV. - **URL**: https://apify.com/fetch_cat/instagram-ai-transcript-extractor.md - **Developed by:** [Fetch Cat](https://apify.com/fetch_cat) (community) - **Categories:** Social media, Videos, AI - **Features:** Limited permissions - **Stats:** 11 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $10.00 / 1,000 item extracteds 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 Turn public Instagram Reels and video posts into transcript text, available timestamped segments, and structured media metadata. The Instagram AI Transcript Extractor accepts video URLs and returns a status row for each unique URL processed. It does not collect whole profiles or transcribe private media. ### Quick start 1. Paste a public Instagram Reel or video URL into **Public Reel or video URLs**. 2. Start with one URL and English speech. Run the Actor and open the dataset. 3. Read `transcriptText` from rows where `status` is `succeeded`, then export JSON, CSV, or Excel. Inspect `errorType` and `errorMessage` on other rows. ```json { "startUrls": [{ "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" }], "maxItems": 1, "language": "en", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": ["RESIDENTIAL"] } } ``` Prefer a video guide? This short Apify walkthrough shows you how to set up and run an Actor. It uses a different Actor, but the setup steps are the same. https://youtu.be/1OW8gOqlZbY?t=25 ### Ready-to-run examples Choose a public example to see its settings before starting a run: - [Extract Instagram Reel Transcript with Timestamps](https://apify.com/fetch_cat/instagram-ai-transcript-extractor/examples/extract-instagram-reel-transcript) ### What you get One per-input status row for each unique normalized public video URL processed, with successful speech transcripts and available segment-level timing. Public media metadata is best effort and can be null. Failed rows explain why transcription was unavailable rather than supplying fabricated transcript text. ### Who is it for? - **Content editors** using returned spoken text as source material for their own summaries or briefs. - **Creator-research teams** reviewing public messaging alongside available media context. - **Video researchers** keeping transcript text, source URLs and timing where supplied. - **Automation developers** routing successful transcripts and failed-input reasons to different downstream steps. ### How you can use the data - **Review one known public Reel.** Use the supplied DPR-1mcCAqa URL with a one-input cap and English speech. Read transcriptText only on a succeeded row, then open the media when wording matters. This is transcription of audio rather than extraction of the Instagram caption. - **Prepare a time-linked text review.** Keep available segment start/end times with their text and canonical video URL. These are segment timestamps rather than guaranteed word-level alignment. Enable `includeSubtitles` for ready-to-save SRT and WebVTT text when timing validates. The accepted includeSegments switch currently does not remove timing. - **Keep text separate from uncertain creator metadata.** Retain shortcode, canonical URL and available caption or owner fields for context. Missing owner information is not an authoritative profile record, and an Instagram caption is separate from the spoken transcript. - **Handle mixed outcomes in your own workflow.** Send succeeded rows to a review or summary step and keep failed rows with errorType and errorMessage. Input order is preserved after normalized duplicate URLs are removed, subject to the cap. A failed lookup does not establish privacy or deletion, and successful inputs in the same batch remain useful. ### Input settings | Setting / API key | Description | | --- | --- | | Public Reel or video URLs / `startUrls` | Required list of Instagram `/reel/`, `/p/`, or `/tv/` URLs containing public video. | | Maximum URLs / `maxItems` | Maximum unique inputs to process. Default `3`, form range `1`–`100`. | | Speech language / `language` | English (`en`) by default. `auto` is accepted, but multilingual transcription is not established for the bundled English model. | | Timestamped segments / `includeSegments` | Accepted but currently does not suppress segments. Available timestamps are returned regardless of this value. | | Subtitle files and batch recovery / `includeSubtitles` | Optional, default `false`. Adds inline SRT/WebVTT, safe filenames, timing warnings and source-associated advisory recovery. No extra transcription or automatic retries. | | Proxy configuration / `proxyConfiguration` | Connection settings. See field help for supported managed options and omitted-input behavior. | #### Example inputs Use the Quick start input as a small first run. Adjust the fields described above for your own data. ### Output data Each processed unique input has a row. Successful rows have `status: "succeeded"` and transcript text. Other rows have `status: "failed"` with a reason. This row status is not the platform run status. Illustrative shape only, not a measured transcript or timing result: ```json { "inputUrl": "https://www.instagram.com/reel/DPR-1mcCAqa/", "canonicalUrl": "https://www.instagram.com/reel/DPR-1mcCAqa/", "shortcode": "DPR-1mcCAqa", "status": "succeeded", "errorType": null, "errorMessage": null, "transcriptText": "Example spoken words.", "segments": [{ "id": 1, "startSeconds": 0, "endSeconds": 2, "text": "Example spoken words." }], "language": "en", "requestedLanguage": "en", "ownerUsername": null, "caption": null, "durationSeconds": null } ``` | Fields | Meaning | | --- | --- | | `inputUrl`, `canonicalUrl`, `shortcode` | Original URL and normalized media identity. | | `status`, `errorType`, `errorMessage` | Per-input outcome and reason when transcription is unavailable. | | `transcriptText`, `segments` | Speech-to-text output and available segment-level timestamps. These are not guaranteed word-level timestamps. Optional subtitle files are delivered separately in `subtitlePackage`. | | `language`, `requestedLanguage` | Requested language and output language label. `language` is null for `auto`, not detected-language proof. | | `durationSeconds` | Original video duration when available. | | `ownerUsername`, `ownerId`, `caption`, `mediaType`, `mediaId` | Best-effort public metadata. Values can be null and are not authoritative profile records. | | `videoUrlFound`, `videoContentLength` | Whether video was discovered and downloaded video bytes. The byte count is null for audio-only downloads. | | `transcriptionSource`, `asrModel` | Method and model labels. | | `scrapedAt`, `metadata` | Collection timestamp and acquisition diagnostics, including HTTP status and available audio/video byte counts. | #### Save and import subtitles; isolate failed clips Set `"includeSubtitles": true` alongside your existing inputs. Every row then includes `subtitlePackage`; omitted or `false` leaves historical output unchanged. `includeSegments` remains accepted and inert. 1. For each `subtitlePackage.available: true` row, save `files.srt.text` as UTF-8 using `files.srt.filename`, or `files.vtt.text` using `files.vtt.filename`. Import the saved file into your editor. These are inline strings, not download URLs or extra Apify storage files. Safe deterministic names include the source shortcode and an identity hash to keep clips associated without path characters. 2. Keep the row's `canonicalUrl` and `subtitlePackage.source` with the saved file. `timing` reports `precision: "segment"`, `origin: "existing_asr_segments"`, validated status and cue count. Millisecond formatting is not word-level accuracy, alignment or speaker attribution. Speech recognition errors remain possible. 3. When `available` is false, `files` is null. Read `warnings` and `recovery.action`. Source transcription failures carry the original `errorType` under `recovery` and `automaticRetry: false`. The existing `inputUrl` remains the source reference for invalid URLs without a canonical identity. Review only affected sources; do not resubmit successful clips. No automatic retry or assertion of retryability is made. Missing/nonfinite/negative/overlapping/out-of-duration or sub-millisecond-collapsed timing suppresses the entire subtitle payload for that row. Transcript text, segments and row status stay unchanged, so a usable transcript can have unavailable subtitles. Markup is escaped and whitespace/control characters normalized in subtitle text, with a warning; original segments are never rewritten. For plain text segments the same ordered words and rounded millisecond times are retained. The option uses already-computed segments, with no extra source request, ASR pass or item fee. It adds two inline text representations and validation/provenance bytes to dataset storage and downstream transfer. Larger transcripts produce larger exports. The existing Overview/export column order is unchanged; use raw dataset JSON (without the Overview view) or explicitly select `subtitlePackage` to obtain the nested text. Existing saved tasks remain unchanged. #### Download your results Open your run's dataset, choose **Export** and select JSON, CSV or Excel. JSON keeps nested fields together. CSV and Excel are useful when you want to review the records in a spreadsheet. See [Apify's download and export guide](https://docs.apify.com/storage/dataset#apify-console) for the available formats and field options. ### Pricing The `start` event is charged once per run, and `item` applies to each successful transcript row. Failed or status-only rows do not incur an item charge, while the startup charge still applies. Begin with a small input cap. Consult the live [Pricing tab](https://apify.com/fetch_cat/instagram-ai-transcript-extractor/pricing) for current rates and announced changes. ### Tips for best results - **Start with one anonymously accessible public video and English speech.** No login or cookie input is supported. - **Read row status before using transcript text.** A platform run outcome and individual transcription outcome are different fields. - **Review unclear speech against the media.** Noise, music, overlap and silence can affect accuracy or leave no usable transcript. - **Keep segment timing only when actually supplied.** Do not turn missing timing into invented word-level alignment. - **Read failure reasons before retrying a target.** Temporary access restrictions can prevent transcription without establishing deletion or privacy. ### Limits and caveats Only anonymously accessible public Instagram video URLs are supported. There is no private-media access, whole-profile discovery, login or cookie input. Public availability can change, and a transcript is not guaranteed for every target. Longer videos can exceed the run time limit. English speech is the supported baseline. Auto is accepted but does not establish multilingual support or detected-language proof, and its language output is null. Noise, music, overlapping speakers, silence or unclear speech can produce inaccurate or empty text. Speaker diarization and translation are not provided. SRT/WebVTT text is available only through the default-off `includeSubtitles` option when existing segment timing validates. Segment timestamps depend on transcription output and are not guaranteed word-level timings. includeSegments currently has no suppressing effect. Owner, caption and other media fields are best effort rather than complete or authoritative profile data. Captions are not the source of the audio transcript, and video byte counts can be null for audio-only acquisition. Rows carry individual succeeded or failed outcomes separately from platform run status. Inspect errorType and errorMessage on failed inputs and preserve useful successes. Unavailable pages do not by themselves prove that a post became private or was deleted. Any summarization or repurposing is your own downstream step. ### Automation and integrations #### Save your settings for next time Once you have an input that works for you, [save it as an Apify task](https://docs.apify.com/actors/running/tasks). This keeps your settings together so you can use them again without filling in the form from scratch. #### Run on a schedule Need fresh results regularly? You can [schedule the Actor or a saved task](https://docs.apify.com/actors/running/schedules) to run at a time that suits you. Each scheduled run collects the data again. If you want to compare results or highlight changes, add that step in your own workflow. #### Send results to your other tools Use **n8n, Make or Zapier** to connect this scraper to the rest of your workflow. For example, you could pass its results to an AI assistant or add records to a spreadsheet. Follow the [Apify integration guides](https://docs.apify.com/integrations) for your chosen tool. For a custom connection, an [Apify webhook](https://docs.apify.com/integrations/webhooks) can notify your app when a run finishes or fails. Your app can then fetch the results or handle the failure. ### API usage Want to collect this data from your own app or automation? The examples below send input to the scraper and show how to collect its results. The Node.js and Python examples wait for the run to finish before reading its results. The cURL example starts the run and returns its details. Wait for that run to finish, then use its `defaultDatasetId` to fetch the results. For setup instructions, see Apify's [JavaScript client guide](https://docs.apify.com/api/client/js), [Python client guide](https://docs.apify.com/api/client/python) and [Actor runs API reference](https://docs.apify.com/api/v2/acts-runs-post). #### cURL ```bash curl -X POST 'https://api.apify.com/v2/acts/fetch_cat~instagram-ai-transcript-extractor/runs' \ -H "Authorization: Bearer $APIFY_TOKEN" \ -H 'Content-Type: application/json' \ --data @- <<'JSON' { "startUrls": [ { "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" } ], "maxItems": 1, "language": "en", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } JSON ``` #### Node.js ```javascript import { ApifyClient } from 'apify-client'; const client = new ApifyClient({ token: process.env.APIFY_TOKEN }); const run = await client.actor('fetch_cat/instagram-ai-transcript-extractor').call({ "startUrls": [ { "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" } ], "maxItems": 1, "language": "en", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }); const { items } = await client.dataset(run.defaultDatasetId).listItems(); console.log(items); ``` #### Python ```python import os from apify_client import ApifyClient client = ApifyClient(os.environ['APIFY_TOKEN']) run = client.actor('fetch_cat/instagram-ai-transcript-extractor').call(run_input={'startUrls': [{'url': 'https://www.instagram.com/reel/DPR-1mcCAqa/'}], 'maxItems': 1, 'language': 'en', 'proxyConfiguration': {'useApifyProxy': True, 'apifyProxyGroups': ['RESIDENTIAL']}}) print(client.dataset(run['defaultDatasetId']).list_items().items) ``` ### MCP and AI agents You can ask your AI assistant to collect data with **Instagram AI Transcript Extractor** and help you work with the results. The scraper returns the data, and your assistant can then summarize it, compare records or prepare notes. Connect your assistant through the [Apify MCP server](https://mcp.apify.com/). MCP gives your assistant a way to find this scraper, run it and read the results. Follow the [official setup and sign-in guide](https://docs.apify.com/mcp) for your app. #### Easier setup with an Apify plugin If you use a supported coding assistant, the [official Apify plugin](https://docs.apify.com/agents/plugins) can set up the connection for you. It connects your assistant to Apify and includes instructions for common tasks. Follow the guide for your particular app. #### Use Apify AI in Console Prefer to keep everything in Apify? Open [Apify AI in Console](https://docs.apify.com/account/apify-ai) and ask it to find Fetch Cat's **Instagram AI Transcript Extractor**. You can describe the data you want and ask questions about the results. Apify AI is currently in beta. It asks for confirmation before starting an Actor, and normal run charges apply. #### Choose your assistant - **Claude and Claude Code (Anthropic):** [Apify setup guide](https://docs.apify.com/integrations/claude). - **ChatGPT and Codex (OpenAI):** [Apify setup guides](https://docs.apify.com/integrations/openai). - **Grok Bot (xAI):** [Apify plugin guide](https://docs.apify.com/integrations/grok-bot). - **Gemini CLI (Google):** [MCP server setup guide](https://geminicli.com/docs/tools/mcp-server/). Use the server URL below with the HTTP configuration supported by Gemini CLI. #### Connect just this scraper To keep your setup focused on this scraper, add this server configuration to a compatible MCP client: ```json { "mcpServers": { "apify": { "url": "https://mcp.apify.com?tools=fetch_cat/instagram-ai-transcript-extractor" } } } ``` Sign in to Apify when your client asks. If your client uses a Bearer token instead, follow its setup guide and keep the token in its secure configuration. Configuration formats vary by app, so use the linked guide if your client needs a different format. #### Use Apify's general server Already connected to the general Apify MCP server at `https://mcp.apify.com`? You can use it to find this scraper without adding another server. Ask your assistant to use **Instagram AI Transcript Extractor** by Fetch Cat, or give it the identifier `fetch_cat/instagram-ai-transcript-extractor`. Your assistant can check the available settings and retrieve the results from the returned run. If the run is still working, it should follow that run rather than start it again. Both connection options use Apify's hosted service. #### Example requests - “Use Fetch Cat’s Instagram AI Transcript Extractor to retrieve the public Reel https://www.instagram.com/reel/DPR-1mcCAqa/ with a one-URL cap and English speech. Show transcript text only if its row succeeded, otherwise show the failure reason.” - “Collect the English transcript for the same DPR-1mcCAqa public Reel with a one-URL cap and keep any available segment timestamps and canonical URL. Do not invent word-level timing. Enable includeSubtitles only if ready-to-save segment-level subtitles are wanted.” - “Retrieve the same public Reel with a one-input cap and English speech, then make a review table of its row status, available transcript, caption and owner metadata. Keep caption text separate from spoken words and flag missing fields.” Normal Apify charges apply. Check the [live Pricing tab](https://apify.com/fetch_cat/instagram-ai-transcript-extractor/pricing) before asking your assistant to run a larger batch. ### Pay with x402 If your AI agent has a funded wallet, it can pay for Apify usage through [x402](https://docs.apify.com/integrations/x402). This experimental option lets an agent use Apify without a conventional account. [Apify AGI](https://agi.apify.com/) provides a prepaid API token with a spending cap after payment. Your agent can use that token to run this scraper through the Apify API or an authenticated MCP connection. Some MCP setups also support paying for each request directly. That is a different payment option, so check the official guide for its availability. Follow the official guide for wallet setup, supported payment options and current terms. Apify handles the payments. Keep wallet keys and payment tokens in your agent's secure configuration. #### Other ways for agents to pay Apify also supports **MPP** for prepaid access through AGI and **Skyfire** for eligible Actors. If your agent already uses one of these, see the [agentic payment guide](https://docs.apify.com/agents/payments) to choose the right setup. ### FAQ #### How do I get an Instagram AI transcript? Supply a public Reel/video URL in `startUrls`, run a small input, and read `transcriptText` from successful rows. The Actor transcribes media audio rather than requiring native Instagram captions. #### Can I transcribe private Reels or an entire profile? No. Use public video URLs. Profile collection and access to private media are outside this Actor's scope. #### Can I export Instagram transcripts as CSV or JSON? Yes, through the Apify dataset export or dataset API. JSON preserves nested `segments` most naturally. #### Why are timestamps or creator fields missing? Segments depend on the transcription output. Creator and caption fields depend on available page information and can be null. Neither timestamps nor complete creator metadata are guaranteed. #### Does disabling `includeSegments` remove timestamps? No. The field is accepted but currently has no effect. The output contains whatever segment timing is available. #### How should I handle failed rows? Inspect `errorType` and `errorMessage`, keep useful successes from mixed batches, and check whether the target remains publicly accessible. Do not infer deletion or privacy from inaccessibility alone. ### Related Actors - [Instagram Profile & Posts Scraper](https://apify.com/fetch_cat/instagram-profile-posts-scraper) — Public profile and post collection. - [Instagram Stories & Highlights Scraper](https://apify.com/fetch_cat/instagram-stories-highlights-scraper) — Collect accessible stories and highlights using your own authorized Instagram session. This does not bypass private-profile permissions. - [Instagram Post Details Scraper](https://apify.com/fetch_cat/instagram-post-details-scraper) — Metadata for known post URLs. - [Instagram Related Profiles Scraper](https://apify.com/fetch_cat/instagram-related-profiles-scraper) — Related-profile discovery. - [TikTok AI Transcript Extractor](https://apify.com/fetch_cat/best-tiktok-ai-transcript-extractor) — Transcription for a different short-video platform. ### Support and feedback For custom additions or integrations, email . Found an error or have a feature request? [Open an issue](https://apify.com/fetch_cat/instagram-ai-transcript-extractor/issues) with the run URL, a non-sensitive input example and what you expected. Need help sharing it? See [Apify’s guide to sharing a run when reporting an issue](https://docs.apify.com/account/collaboration/general-resource-access#automatically-sharing-runs-via-actor-issues). Sharing a run can give the developer access to its input, logs and results, so use a run that contains no sensitive data. Please leave out API tokens, passwords, cookies, private documents and personal data. Use a public sample URL or a redacted example instead. Tried this scraper? We'd love to hear how it worked for you. [Leave a review](https://apify.com/fetch_cat/instagram-ai-transcript-extractor/reviews) to help others choose the right tool and help us improve it. Your feedback means a lot to us. Made with care for curious people, AI agents and the possibilities in data. ♥ # Changelog This Actor's version history is a separate document: https://apify.com/fetch_cat/instagram-ai-transcript-extractor/changelog.md # Actor input Schema ## `startUrls` (type: `array`): Public Instagram Reel/video URLs to transcribe. Private, deleted, unsupported, or unavailable media are returned as classified failure rows. ## `maxItems` (type: `integer`): Stops after this many unique input URLs. ## `language` (type: `string`): English (en) is the supported baseline and default. auto is accepted, but the bundled model is English-only: multilingual accuracy is not established, and the output language field is null for auto. ## `includeSegments` (type: `boolean`): This accepted field currently has no effect. Available segment-level timestamps are returned regardless of whether this value is true or false; timing may be absent. ## `includeSubtitles` (type: `boolean`): Return ready-to-save SRT and WebVTT text, safe filenames, segment-timing validation and per-source failure handoff in subtitlePackage. Off by default. Uses existing segments without another download or transcription; adds output bytes, not item charges. No automatic retries or subtitle storage files. Timing is segment-level, not word-accurate. Invalid or absent timing yields warnings, not fabricated subtitles. includeSegments remains unchanged. ## `proxyConfiguration` (type: `object`): The form defaults to managed Apify Proxy with the RESIDENTIAL group. Explicit settings are used as supplied: useApifyProxy true activates the managed configuration for browser and media requests; false disables it. An omitted proxyConfiguration uses direct access in the runtime. Custom proxy URLs alone are not activated by this Actor. No automatic switch or paid fallback is added. Managed proxy usage may incur costs; keep a small input initially. ## Actor input object example ```json { "startUrls": [ { "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" } ], "maxItems": 3, "language": "en", "includeSegments": true, "includeSubtitles": false, "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } ``` # Actor output Schema ## `overview` (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 = { "startUrls": [ { "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" } ] }; // Run the Actor and wait for it to finish const run = await client.actor("fetch_cat/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 = { "startUrls": [{ "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" }] } # Run the Actor and wait for it to finish run = client.actor("fetch_cat/instagram-ai-transcript-extractor").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 '{ "startUrls": [ { "url": "https://www.instagram.com/reel/DPR-1mcCAqa/" } ] }' | apify call fetch_cat/instagram-ai-transcript-extractor --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,fetch_cat/instagram-ai-transcript-extractor" } } } ``` 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/Auo0zQTyZaNCMfHcc/builds/SnwoM623i904wR79u/openapi.json