{ "openapi": "3.0.1", "info": { "title": "Bulk Transcription: Audio & Video to Text from CSV or Sheet", "description": "Transcribes every audio or video link in an Apify dataset, CSV, Excel or Google Sheet, keeping your columns. Inputs: datasetId or fileUrl or mediaUrls, urlField, mode (plain text, or speakers with timestamps and SRT). Charged per started minute of audio. Agent-ready: x402, MCP.", "version": "0.1", "x-build-id": "TN6hUqfMtyNRjd11p" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nerolabs~bulk-transcription/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nerolabs-bulk-transcription", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nerolabs~bulk-transcription/runs": { "post": { "operationId": "runs-sync-nerolabs-bulk-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nerolabs~bulk-transcription/run-sync": { "post": { "operationId": "run-sync-nerolabs-bulk-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetId": { "title": "Dataset", "type": "string", "description": "An Apify dataset holding one row per recording, for example call logs, podcast episodes or a scraper's video links. Every original column is kept and the transcript, duration and speaker count are added alongside. Use the picker rather than typing an ID." }, "fileUrl": { "title": "File or Google Sheet URL", "type": "string", "description": "A public link to a CSV, TSV, Excel, JSON or JSON Lines file holding one row per recording (call recordings, voicemails, podcast episodes, meeting videos). A normal Google Sheets link works: share it as 'Anyone with the link can view'. Used when no dataset is given." }, "fileFormat": { "title": "File format", "enum": [ "auto", "csv", "tsv", "json", "jsonl", "xlsx" ], "type": "string", "description": "Leave on 'Detect automatically' unless the link has no file extension and the server reports the wrong content type.", "default": "auto" }, "sheetName": { "title": "Excel sheet name", "type": "string", "description": "Which sheet to read from an Excel workbook. Defaults to the first sheet." }, "mediaUrls": { "title": "Audio or video URLs", "type": "array", "description": "A plain list of direct links to audio or video files (MP3, WAV, M4A, MP4, MOV, WebM, OGG, FLAC and more; Google Drive and Dropbox share links work), for a quick run with no spreadsheet. Use the dataset, file or Google Sheet inputs above to keep your own columns alongside each transcript.", "items": { "type": "string" } }, "data": { "title": "Rows", "type": "array", "description": "Rows as inline JSON, an alternative to a dataset or file. Each object needs a field holding the audio or video link." }, "urlField": { "title": "Recording URL field", "type": "string", "description": "The column holding the audio or video link. Left empty it is detected automatically, preferring a column whose values end in .mp3, .wav, .m4a or .mp4 over one merely named 'url'." }, "mode": { "title": "Transcript type", "enum": [ "text", "detailed" ], "type": "string", "description": "'Plain text' is the cheapest: one block of text per file. 'Speakers and timestamps' labels who spoke (Speaker A, Speaker B), gives start and end times, and writes SRT subtitles, for calls, interviews, meetings and podcasts. Each is charged per started minute of audio at its own rate.", "default": "text" }, "language": { "title": "Language", "type": "string", "description": "Two-letter code of the spoken language (en, es, fr, de, pt, it, nl, pl, ja, zh and about 50 more). Leave empty to detect it automatically; setting it helps accuracy on short or noisy clips." }, "vocabulary": { "title": "Spelling hints", "type": "string", "description": "Plain text mode only. Names, brands or jargon the recording uses, for example 'NICEIC, consumer unit, Part P, Brightwell'. Helps the model spell them right." }, "includeSrt": { "title": "Include SRT subtitles", "type": "boolean", "description": "Speakers mode only. Adds an 'srt' column with ready-to-use subtitles for the recording.", "default": true }, "includeSegments": { "title": "Include timed segments", "type": "boolean", "description": "Speakers mode only. Adds a 'segments' array: one entry per speaker turn with speaker, start, end and text. Useful for feeding an AI agent or building your own player.", "default": false }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Only the first this-many minutes of each file are transcribed and charged. Your cost ceiling per file: a 6-hour livestream cannot run up a bill you did not expect.", "default": 120 }, "keep": { "title": "Which rows to keep", "enum": [ "all", "ok", "problems" ], "type": "string", "description": "Filtering happens after the file has been processed, so it does not make a run cheaper. 'Problems only' is the quick way to find broken links and unsupported files in a large list.", "default": "all" }, "keepOriginalFields": { "title": "Keep my original columns", "type": "boolean", "description": "Keep every column from the input row next to the transcript, so results line up with your own data (call ID, date, client, episode title). Turn off for transcripts and counts only.", "default": true }, "concurrency": { "title": "Files at a time", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many files to work on in parallel. Transcription runs on a remote speech service, so this is mostly limited by download speed; 3 suits the default memory.", "default": 3 }, "requestTimeoutSecs": { "title": "Download timeout", "minimum": 5, "maximum": 600, "type": "integer", "description": "How long to wait for one file to download before giving up on it. A timed-out file is never charged.", "default": 120 }, "maxFileMb": { "title": "Largest file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Files bigger than this are skipped and not charged. Video files are large; only their audio is used.", "default": 500 }, "maxItems": { "title": "Maximum files", "minimum": 1, "maximum": 50000, "type": "integer", "description": "A hard ceiling on how many rows are read from the input, as a safety net on a large dataset." }, "exportFormats": { "title": "Export files", "type": "array", "description": "Also write the results as a real downloadable CSV or Excel file, linked from the run's output. Timed segments are JSON-encoded into a single cell so they fit a spreadsheet.", "items": { "type": "string", "enum": [ "csv", "xlsx" ], "enumTitles": [ "CSV", "Excel (xlsx)" ] }, "default": [] }, "outputDatasetName": { "title": "Append to named dataset", "type": "string", "description": "Also append every kept row to a named dataset that persists across runs, building one growing transcript archive. Not charged again." }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "POST the run summary to this URL when the run finishes, for Slack, Zapier, Make, n8n or your own API. Charged only on a confirmed 2xx response." } } }, "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 } } } } } } } } } }