{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript AI: Subtitles, SRT & Speakers", "description": "AI YouTube transcription from the audio, so videos with no captions work too. Get a timestamped YouTube transcript with word timings, speaker labels and SRT/VTT subtitles for videos, Shorts and finished livestreams. 90+ languages, about $0.001/min. No login or API key.", "version": "0.1", "x-build-id": "TFVsDD0Uof1sOsCXg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/deapi~youtube-transcript-ai/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-deapi-youtube-transcript-ai", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/deapi~youtube-transcript-ai/runs": { "post": { "operationId": "runs-sync-deapi-youtube-transcript-ai", "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/deapi~youtube-transcript-ai/run-sync": { "post": { "operationId": "run-sync-deapi-youtube-transcript-ai", "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": "YouTube video URLs", "minItems": 1, "type": "array", "description": "Links to YouTube videos. Regular videos (`youtube.com/watch?v=…`), short links (`youtu.be/…`), **Shorts** (`youtube.com/shorts/…`) and **finished livestreams** (`youtube.com/live/…`) all work, and `m.youtube.com`, `music.youtube.com` and embed links are rewritten for you. The audio is transcribed, so videos **without captions** work too. Playlist and channel pages are rejected — paste the individual videos. A stream that is still live cannot be transcribed until it ends. Maximum 10 hours per video. Private, deleted and region-locked videos are detected before anything is charged. **Free plan: 3 videos per run, 30 minutes maximum each, 60 transcribed minutes per calendar month (resets 00:00 UTC on the 1st), within a daily capacity shared by all free users. Paid plans remove every limit.**", "items": { "type": "string" } }, "timestampLevel": { "title": "Timestamp level", "enum": [ "none", "segment", "word" ], "type": "string", "description": "How finely the transcript is timed. **Segment** gives one timestamp per sentence — right for subtitles, reading, chapters and jumping to the moment something was said, and included in the base price. **Word** times every single word — right for clip cutting, word-by-word captions and search. **None** returns plain text only. Word moves the video onto the precision rate ($0.01063 per video + $0.00154 a minute, against $0.0075 + $0.00106), and choosing speaker labels as well costs nothing extra on top.", "default": "segment" }, "diarize": { "title": "Label speakers (diarization)", "type": "boolean", "description": "Detect who is speaking and tag every line with a speaker (SPEAKER_00, SPEAKER_01, …). Use it for podcasts, interviews, panels, webinars and any video with more than one voice. Speaker labels need timing to attach to, so switching this on together with **None** still returns sentence-level timing. Moves the video onto the precision rate ($0.01063 per video + $0.00154 a minute, against $0.0075 + $0.00106); if you already picked Word timestamps, adding speakers costs nothing extra.", "default": false }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "es", "pt", "fr", "de", "it", "nl", "pl", "uk", "ru", "tr", "ar", "he", "hi", "id", "ms", "vi", "th", "ja", "ko", "zh", "sv", "da", "no", "fi", "cs", "ro", "el", "hu" ], "type": "string", "description": "Pick the language spoken in the video whenever you know it. Auto-detect can misidentify the language, which lowers transcription accuracy. One language applies to every URL in the run, so split mixed-language batches into separate runs, or keep auto-detect and check `languageConfidence` in the output. The dropdown lists the 29 most requested languages; anything else is transcribed on auto-detect.", "default": "auto" }, "includeSubtitles": { "title": "Add SRT and VTT subtitles", "type": "boolean", "description": "Return ready-to-use subtitle files as `srt` and `vtt` fields — paste them straight into a video editor, a player or a CMS. Free of charge. Subtitles need timing to exist, so they are produced at every timestamp level except None, and also at None when speaker labels are switched on. On very long videos the files are saved to the run's key-value store and linked as `srtUrl` and `vttUrl` instead of being inlined, so nothing is ever truncated.", "default": true }, "includeMetadata": { "title": "Add video metadata", "type": "boolean", "description": "Attach the video's own data to each row: title, channel, description, view count and like count. Turns one run into transcript + video context for content research. Optional add-on of $0.00625 per video — leave it off and you are not charged for it.", "default": false }, "maxConcurrency": { "title": "Videos in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many videos are transcribed at the same time. Higher finishes a large batch sooner. It has no effect on price — you are charged per video and per minute of audio either way, and platform usage is on us.", "default": 3 } } }, "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 } } } } } } } } } }