{ "openapi": "3.0.1", "info": { "title": "Instagram Reels Transcript - Reel to Text & SRT", "description": "Transcribe public Instagram Reels to text, timestamped segments, SRT and VTT. Instagram publishes no caption track, so every Reel is transcribed with Whisper speech-to-text — which is exactly why Reels without captions still come back as text. Public content only: no login, no cookies.", "version": "1.0", "x-build-id": "A4N5oTBWl3vaS9T3H" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sauliusautomatesit~instagram-reels-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sauliusautomatesit-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sauliusautomatesit~instagram-reels-transcript/runs": { "post": { "operationId": "runs-sync-sauliusautomatesit-instagram-reels-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sauliusautomatesit~instagram-reels-transcript/run-sync": { "post": { "operationId": "run-sync-sauliusautomatesit-instagram-reels-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "videoUrls" ], "properties": { "videoUrls": { "title": "Instagram Reel URLs", "minItems": 1, "type": "array", "description": "Public Instagram Reel URLs to transcribe — one per line, from a single link to thousands. `instagram.com/reel/CODE/`, `instagram.com/reels/CODE/`, `instagram.com/USER/reel/CODE/`, `/p/CODE/` and `/tv/CODE/` all work. Profile and explore URLs are not single Reels and will be reported as errors.", "items": { "type": "string" } }, "language": { "title": "Spoken language", "type": "string", "description": "Two-letter language code (`en`, `es`, `pt`, `ar`, `fr`…). Leave blank to let Whisper detect the language — that is the default and it is usually right. Setting it helps on short or noisy Reels where detection can pick the wrong language." }, "allowWhisperFallback": { "title": "Transcribe the audio with Whisper", "type": "boolean", "description": "On (default), and it needs to stay on. Instagram publishes no caption track to a logged-out viewer, so Whisper speech-to-text is the only way a Reel becomes text — every successful row is charged `asr_transcript`. Turning this off makes every Reel return a free `CAPTIONS_UNAVAILABLE` error, which is useful only as a way to stop the Actor spending anything.", "default": true }, "maxDurationSeconds": { "title": "Maximum Reel length (seconds)", "minimum": 5, "maximum": 1200, "type": "integer", "description": "Reels longer than this are skipped with a `DURATION_EXCEEDED` error and are not charged.", "default": 600 }, "maxAsrDurationSeconds": { "title": "Maximum length to transcribe (seconds)", "minimum": 5, "maximum": 1200, "type": "integer", "description": "Whisper costs roughly a second of CPU per 1.5 seconds of audio, so a per-video price only works up to a point; past this length a Reel returns `ASR_DURATION_EXCEEDED` and costs nothing. The default of 180 s covers the great majority of Reels. Instagram does not tell an anonymous viewer how long a Reel is, so this is enforced from the downloaded audio's own header — before transcription starts, and before anything is charged.", "default": 180 }, "maxVideos": { "title": "Maximum Reels per run", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Safety cap on how many URLs from the list are processed.", "default": 1000 }, "whisperModel": { "title": "Whisper model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Accuracy vs speed. `base` is the recommended balance; `small` is noticeably better on accented speech and noisy audio, and noticeably slower.", "default": "base" }, "beamSize": { "title": "Whisper beam size", "minimum": 1, "maximum": 5, "type": "integer", "description": "Decoding beam width. 1 is fastest; higher is marginally more accurate and slower.", "default": 1 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many Reels to resolve at once. Whisper transcription is always serialised regardless of this setting, to keep the run inside its memory limit.", "default": 5 }, "includeFailedItems": { "title": "Include failed Reels in the dataset", "type": "boolean", "description": "On (default): unavailable, private, too-long and non-Instagram URLs get a dataset row carrying an `error` code, so you can reconcile inputs to outputs. Failed rows are never charged.", "default": true }, "useResidentialFallback": { "title": "Retry on a residential IP when Instagram refuses the request", "type": "boolean", "description": "On (default), and worth leaving on. Instagram refuses far more datacenter addresses than the other short-form platforms do; when it answers the normal proxy with a bot check or a login wall, that one request is retried through Apify's residential proxy. Only requests the cheap route already refused use it.", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy used to reach Instagram. Apify Proxy is recommended: the run pins one proxy session so that a Reel's media file is fetched from the same IP that resolved it, which is what Instagram's CDN requires.", "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 } } }, "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 } } } } } } } } } }