{ "openapi": "3.0.1", "info": { "title": "Audio Transcription - Deepgram Nova-3, SRT, Diarization", "description": "Transcribe audio and video URLs — speech-to-text with Deepgram Nova-3. Whisper alternative for meeting transcription, podcast transcripts, and SRT subtitles. Speaker diarization, summaries, language detection. Zero setup $0.010/min or BYOK $0.004/min.", "version": "0.0", "x-build-id": "dXWBOwfv4WSxdklA2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kaz_kakyo~audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kaz_kakyo-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/kaz_kakyo~audio-transcriber/runs": { "post": { "operationId": "runs-sync-kaz_kakyo-audio-transcriber", "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/kaz_kakyo~audio-transcriber/run-sync": { "post": { "operationId": "run-sync-kaz_kakyo-audio-transcriber", "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": [ "audioUrls" ], "properties": { "audioUrls": { "title": "Audio / video file URLs", "minItems": 1, "type": "array", "description": "Required. Direct https links to media files (mp3, wav, m4a, flac, ogg, opus, mp4, mov, webm, mkv — up to 2 GB each). One dataset row per URL; max 500 per run. Minimal call: only this field. Do NOT pass YouTube/Spotify/SoundCloud/Vimeo/Apple Podcasts page URLs or Drive/Dropbox share pages — resolve to a direct or signed file URL first. Bad URLs become type:error rows; the run still succeeds.", "items": { "type": "string" } }, "deepgramApiKey": { "title": "Deepgram API key (optional — cuts the price to $0.004/min)", "type": "string", "description": "Optional. Leave empty for zero-setup at $0.010/min. Or bring your own free Deepgram key (console.deepgram.com — $200 credit, no card) and pay $0.004/min here plus Deepgram's wholesale ~$0.0043/min directly. Best for scheduled/API volume. Stored encrypted; sent only to api.deepgram.com." }, "model": { "title": "Model", "enum": [ "nova-3", "nova-2", "whisper-large" ], "type": "string", "description": "Speech model. Default `nova-3` (fast, accurate, multilingual). `nova-2` = previous generation; `whisper-large` = rarer languages (runs at lower concurrency).", "default": "nova-3" }, "language": { "title": "Language", "type": "string", "description": "Optional BCP-47 code (e.g. `en`, `es`, `zh`, `de`). Leave empty for English, or set `detectLanguage`. Use `multi` with nova-3 for code-switched audio." }, "detectLanguage": { "title": "Detect language automatically", "type": "boolean", "description": "Default: false. When true, detect the dominant language per file and transcribe in it. Overrides `language`.", "default": false }, "diarize": { "title": "Speaker diarization", "type": "boolean", "description": "Default: false. When true, adds `speakerTranscript` (`Speaker 0: …`) and speaker labels on SRT/utterances/words. Typical for meetings and interviews.", "default": false }, "smartFormat": { "title": "Smart formatting", "type": "boolean", "description": "Default: true. Punctuation plus formatted dates, numbers, currency, phones, and emails in `transcript`.", "default": true }, "paragraphs": { "title": "Paragraph breaks", "type": "boolean", "description": "Default: true. Split `transcript` into readable paragraphs instead of one wall of text.", "default": true }, "summarize": { "title": "Summary", "type": "boolean", "description": "Default: false. When true, adds `summary` (short abstract). English audio only — ignored for explicit non-English `language`.", "default": false }, "includeSrt": { "title": "SRT subtitles", "type": "boolean", "description": "Default: false. When true, adds `srt` (ready-to-save `.srt` string; speaker tags when `diarize` is on).", "default": false }, "includeUtterances": { "title": "Utterance timestamps", "type": "boolean", "description": "Default: false. When true, adds `utterances[]`: `{ start, end, speaker, text }` per spoken segment. Useful for programmatic indexing.", "default": false }, "includeWords": { "title": "Word-level timestamps", "type": "boolean", "description": "Default: false. When true, adds `words[]` with per-word timing and confidence. Large output on long audio — prefer utterances for most pipelines.", "default": false }, "keyterms": { "title": "Key terms (nova-3 only)", "type": "array", "description": "Optional. Product names, jargon, or speaker names to boost recognition (nova-3 keyterm prompting). Ignored on other models.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }