{ "openapi": "3.0.1", "info": { "title": "Instagram Reels Transcript Scraper - Speech to Text, No Login", "description": "Public Instagram Reels turned into text: full spoken transcript, timed segments and the Reel's own metadata. No login, no cookies.", "version": "0.2", "x-build-id": "EbWW5FxGrJ6XrM3Ju" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lanternlab318~instagram-reels-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lanternlab318-instagram-reels-transcript", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lanternlab318~instagram-reels-transcript/runs": { "post": { "operationId": "runs-sync-lanternlab318-instagram-reels-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lanternlab318~instagram-reels-transcript/run-sync": { "post": { "operationId": "run-sync-lanternlab318-instagram-reels-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "reelUrls" ], "properties": { "reelUrls": { "title": "Reel links or public accounts", "type": "array", "description": "One entry per line. A Reel link in any shape Instagram serves it (/reel/, /reels/, /p/, /tv/), or a public account name such as \"natgeo\" or \"@natgeo\" to take that account's most recent Reels. Only public Reels are read: this Actor never logs in and never uses a cookie.", "items": { "type": "string" } }, "allowAsr": { "title": "Listen to the Reel when there is no caption track", "type": "boolean", "description": "Instagram shows no caption track to a logged-out visitor, so with this off almost every Reel comes back with metadata and no transcript. Leave it on to have the spoken words transcribed by the speech model inside this Actor.", "default": true }, "language": { "title": "Spoken language", "type": "string", "description": "Two-letter code of the language spoken in the Reels, for example \"pt\" for Portuguese, \"es\" for Spanish, \"id\" for Indonesian, \"zh\" for Chinese. Leave it empty unless every Reel in the run really is in that language: the model otherwise detects the language per Reel, and forcing the wrong one both garbles the transcript and makes the run far slower. Measured on one 144 s Reel from a Brazilian account that turned out to be narrated in English: 8.7 s transcribed with the language detected, against 47.6 s and an unusable transcript with \"pt\" set." }, "includeSegments": { "title": "Include the timed transcript", "type": "boolean", "description": "Adds segments: one entry per spoken passage with its start and end in seconds. Turn it off for the plain text only, which is smaller to store and enough to feed an LLM.", "default": true }, "maxDurationSec": { "title": "Skip Reels longer than (seconds)", "minimum": 1, "maximum": 3600, "type": "integer", "description": "A Reel longer than this is returned with its metadata, marked partial with partialReason \"duration_exceeded\", and is not transcribed or charged. This is the guard that keeps one unusually long video from dominating a run.", "default": 60 }, "maxItems": { "title": "Max Reels per account", "minimum": 1, "maximum": 100, "type": "integer", "description": "Applies to account entries only: how many of the account's most recent Reels to read. A Reel link always produces exactly one row. Instagram's public profile page itself offers about a dozen recent posts, so an account rarely yields more than that.", "default": 10 }, "maxUpstreamRequests": { "title": "Max Instagram requests", "minimum": 1, "type": "integer", "description": "Hard ceiling on the HTTP requests this run sends to Instagram: Reel pages, profile pages, audio downloads and proxy retries together. At the ceiling collection stops - the entries not reached are written with partialReason \"upstream_request_cap\" and the run then ends normally. Leave empty and the Actor works a ceiling out from your input, so a run is never unbounded." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy used for the Reel pages. Apify Proxy datacenter is enough for them. Public profile pages are always fetched through a residential IP, because Instagram answers a datacenter IP with a login redirect for those; the Reel audio is downloaded from Instagram's CDN without a proxy.", "default": { "useApifyProxy": true } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }