{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber (Whisper, SRT, TikTok, Podcasts)", "description": "Super cheap Whisper transcription: about $0.04 per hour of audio. Paste a file or TikTok/Instagram link, get text with timestamps, word timings, speaker labels and SRT/VTT subtitles in 99 languages. Private: nothing is stored.", "version": "1.0", "x-build-id": "UH7sM7SKJ3EH5dlkM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/unsavedai-tools~unsavedai-transcribe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-unsavedai-tools-unsavedai-transcribe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/unsavedai-tools~unsavedai-transcribe/runs": { "post": { "operationId": "runs-sync-unsavedai-tools-unsavedai-transcribe", "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/unsavedai-tools~unsavedai-transcribe/run-sync": { "post": { "operationId": "run-sync-unsavedai-tools-unsavedai-transcribe", "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": [ "url" ], "properties": { "url": { "title": "Media file or video page URL", "type": "string", "description": "A direct link to an audio or video file (.mp4, .m4a, .mp3, .webm, .ogg ...), or the normal page link of a TikTok, Instagram, X or similar video: its audio is fetched for you. Page links are best effort, because some platforms block cloud servers (YouTube links are not supported yet)." }, "max_minutes": { "title": "Max minutes", "minimum": 1, "maximum": 30, "type": "integer", "description": "Transcribe (and pay for) at most this many minutes. Longer media is cut and flagged 'truncated'.", "default": 10 }, "language": { "title": "Language", "type": "string", "description": "Whisper language code such as 'en', 'es', 'zh'. Leave empty to auto-detect." }, "segments": { "title": "Timestamped segments", "type": "boolean", "description": "Add the transcript as timestamped segments with confidence.", "default": true }, "words": { "title": "Word timings", "type": "boolean", "description": "Add start/end time and confidence for every word.", "default": false }, "speakers": { "title": "Speaker labels (beta, paid add-on)", "type": "boolean", "description": "Who spoke when: a speaker on every segment and word, plus speaker turns. Up to 20 minutes per run.", "default": false }, "num_speakers": { "title": "Number of speakers (if known)", "minimum": 1, "maximum": 10, "type": "integer", "description": "With speaker labels: how many people speak. Improves accuracy." }, "srt": { "title": "SRT subtitles", "type": "boolean", "description": "Also return the transcript as SRT subtitles (in the srt field). Cues start with S1:, S2: and so on when speaker labels are on.", "default": false }, "vtt": { "title": "WebVTT subtitles", "type": "boolean", "description": "Also return the transcript as WebVTT subtitles (in the vtt field), for HTML5 video players.", "default": false } } }, "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 } } } } } } } } } }