{ "openapi": "3.0.1", "info": { "title": "Instagram AI Transcript Extractor", "description": "Instagram Reel transcript extractor. Address by Reel URL, bulk list or whole channel. Returns AI transcription with speaker diarization, word-level timestamps, detected language, SRT and WebVTT subtitles, and 30+ metadata fields per reel.", "version": "2.1", "x-build-id": "X9SgzGENnw8S1EDF2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sian.agency~instagram-ai-transcript-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sian.agency-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sian.agency~instagram-ai-transcript-extractor/runs": { "post": { "operationId": "runs-sync-sian.agency-instagram-ai-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sian.agency~instagram-ai-transcript-extractor/run-sync": { "post": { "operationId": "run-sync-sian.agency-instagram-ai-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "instagramUrl": { "title": "🎬 Single Instagram URL", "pattern": "^https://(www\\.|m\\.)?instagram\\.com/(reels?|p)/[A-Za-z0-9_-]+/?.*$", "type": "string", "description": "🎬 **SINGLE VIDEO:** transcribe one Instagram Reel or video post per run.\n\nπŸ“± Open the reel/post β†’ **Share (↗️)** β†’ **Copy Link** β†’ paste here.\n\nβœ… **Works:** `/reel/` and `/p/` URLs holding a **video with spoken audio**. `/reels/` is auto-corrected to `/reel/`.\n\n❌ **Not supported:** image carousels/slideshows, music-only clips, silent video. **Public profiles only.**\n\nπŸ’‘ For several videos use **Bulk Instagram URLs** below instead.", "default": "https://www.instagram.com/p/DS46KJNjva9/" }, "bulkUrls": { "title": "πŸš€ Bulk Instagram URLs (Multiple Videos)", "type": "array", "description": "πŸš€ **BULK PROCESSING:** transcribe many Instagram videos in a single run.\n\nπŸ’° **Tier limits:** FREE accounts **5 URLs per run**; paid accounts unlimited.\n\nπŸ“ **Bulk edit** β€” paste one URL per line.\nπŸ“ **Upload a .txt file** β€” line breaks, commas and spaces all work.\nπŸ”— **+ Add** β€” enter URLs one at a time.\n\n⚠️ Provide **either** a single URL **or** bulk URLs β€” at least one is required.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "wordLevelTimestamps": { "title": "πŸ”€ Word-Level Timestamps (FREE)", "type": "boolean", "description": "πŸ”€ **WORD-LEVEL TIMING:** a start/end timestamp for every single word, returned in the `words` field.\n\nπŸ†“ **Free** β€” no extra charge, on both free and paid accounts.\n\n🎯 **Use it for:** frame-accurate subtitles and captions, syncing edits in a video editor, finding the exact moment a word is spoken, and speech-pattern, research or accessibility work.\n\n✨ In bulk and channel runs it applies to **every** video, still at no extra cost.", "default": false }, "speakerDiarization": { "title": "πŸ—£οΈ Speaker Diarization (FREE)", "type": "boolean", "description": "πŸ—£οΈ **WHO SAID WHAT:** labels every segment and word with a speaker id (`SPEAKER_00`, `SPEAKER_01`, …) in the `speaker` field.\n\nπŸ†“ **Free** on both free and paid accounts.\n\n🎯 **Turn it on for:** interviews, podcasts, duets, street interviews, reaction videos, anything with more than one voice.\n\nπŸ’‘ **Leave it off for single-speaker reels.** Off is faster, and `speaker` comes back `null`.\n\n✨ In bulk and channel runs it applies to **every** video.", "default": false }, "fastProcessing": { "title": "⚑ Fast Processing (PAID add-on)", "type": "boolean", "description": "⚑ **SPEED BOOST:** transcripts 50%+ faster than the standard path (standard β‰ˆ 30 s per video).\n\nπŸ’° **Paid add-on, charged per URL** on top of the per-video fee. Paid accounts pay a lower rate than free ones. Leave off for no extra cost.\n\nβœ… **Worth it for bulk runs (2+ videos)** and time-sensitive monitoring.\n❌ **Not worth it for a single URL** β€” the difference is marginal.\n\n✨ In bulk runs it applies to **all** URLs and is charged for each one.", "default": false }, "includeComments": { "title": "πŸ’¬ Include Pinned & Creator Comments (PAID add-on)", "type": "boolean", "description": "πŸ”’ **Paid plans only.** Free-tier runs return the transcript alone β€” no comments, no charge.\n\nπŸ’¬ Creators often put the real detail (full recipe, ingredients, links) **only in a pinned comment**, not the caption.\n\nπŸ“Š **Adds three fields:** `comments` (pinned first, then top β€” text, author, likes, pinned/creator flags), `pinnedComments` (up to 3 allowed), `creatorComments` (the creator’s own unpinned replies).\n\nπŸ’° Charged only when enabled **and** at least one comment is returned.", "default": false }, "maxComments": { "title": "πŸ”’ Max Comments Per Video", "minimum": 1, "maximum": 200, "type": "integer", "description": "πŸ”’ **CAP THE COMMENTS** returned per video when the comments add-on is on.\n\nπŸ’‘ **Leave empty for the default:** one page of the most relevant comments, exactly as before.\n\nπŸ“Œ **Pinned and creator comments come first**, so a small cap still keeps the ones that matter.\n\n⚠️ **A value above one page fetches MORE pages**, which is slower and costs more. This caps the rows you get back; it does not speed anything up.\n\n🚫 Ignored unless *Include Pinned & Creator Comments* is on." }, "translateTo": { "title": "🌍 Translate Transcript To… (PAID add-on)", "enum": [ "AF", "SQ", "AR", "AN", "HY", "AS", "AY", "AZ", "BA", "EU", "BE", "BN", "BS", "BR", "BG", "MY", "CA", "ZH", "ZH-HANS", "ZH-HANT", "HR", "CS", "DA", "NL", "EN-US", "EN-GB", "EO", "ET", "FI", "FR", "FR-FR", "GL", "KA", "DE", "DE-DE", "EL", "GN", "GU", "HT", "HA", "HE", "HI", "HU", "IS", "IG", "ID", "GA", "IT", "JA", "JV", "KK", "KO", "KY", "LA", "LV", "LN", "LT", "LB", "MK", "MG", "MS", "ML", "MT", "MI", "MR", "MN", "NE", "NB", "OC", "OM", "PS", "FA", "PL", "PT-BR", "PT-PT", "PA", "QU", "RO", "RU", "SA", "SR", "ST", "SK", "SL", "ES", "ES-419", "SU", "SW", "SV", "TL", "TG", "TA", "TT", "TE", "TH", "TS", "TN", "TR", "TK", "UK", "UR", "UZ", "VI", "CY", "WO", "XH", "YI", "ZU" ], "type": "string", "description": "πŸ”’ **Paid plans only** β€” free-tier runs return the original language, uncharged.\n\n🌍 Translates into **100+ languages**. Context-aware AI reads the whole transcript, so slang, idiom and tone survive β€” better than word-by-word. Source language auto-detected.\n\nπŸ’° **Charged per 1,000 transcript characters** (typical reel β‰ˆ 1 unit).\n\nπŸ“Š Adds `translatedTranscript`; `transcript`, `segments`, `words` and timestamps stay in the source language, so timing stays exact. Applies in bulk and channel runs." }, "channelUsername": { "title": "πŸ‘€ Instagram Username or URL (Channel Scrape)", "type": "string", "description": "πŸ‘€ **CHANNEL SCRAPE MODE:** transcribe the most recent reels from one Instagram profile.\n\nπŸ“ **Accepts** a bare username (`yourusername`) or any profile URL β€” including the `/reels/` and `/tagged/` tabs. The username is extracted automatically.\n\n🎯 Set how many reels to take in **Amount of Reels to Scrape** below.\n\n⚠️ When this field is filled, **Single URL and Bulk URLs are ignored**.\n❌ Public profiles only; a reel needs spoken audio to be transcribed." }, "reelCount": { "title": "πŸ”’ Amount of Reels to Scrape", "minimum": 1, "type": "integer", "description": "πŸ”’ How many of the profile's most recent reels to take. Used **only in Channel Scrape mode**.\n\nπŸ’° **Tier limits:** FREE accounts 5 reels per run; paid accounts unlimited.\n\nπŸ”„ Always walks **newest β†’ oldest**, inside the date filter if one is set β€” e.g. `50` + \"last 3 months\" = the 50 most recent reels from the last 3 months.\n\nπŸ“Š Try 10–20 for a quick read, 50–100 for a full content study. Only reels with spoken audio produce a transcript.", "default": 10 }, "onlyPostsNewerThan": { "title": "πŸ“… Only Posts Newer Than (Optional)", "type": "string", "description": "πŸ“… **DATE FILTER (optional):** only take reels newer than this date. Channel Scrape mode only.\n\n🎯 **Two formats:** an absolute date from the calendar, or a relative period such as `1 day`, `3 weeks`, `6 months`.\n\n⚠️ Leave **empty to scrape all available reels** β€” that is the default behaviour.\n⚠️ When set, the date filter is applied **before** the reel-count limit: \"last 3 months\" + `50` = the 50 newest reels from the last 3 months." } } }, "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 } } } } } } } } } }