{ "openapi": "3.0.1", "info": { "title": "CremyX Diarize", "description": "Speaker diarization with sherpa-onnx: returns speaker turns and can label an existing word-level transcript with speaker IDs.", "version": "0.1", "x-build-id": "CTEPvdGbgRNephLwO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/andrew_babo~cremyx-diarize/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-andrew_babo-cremyx-diarize", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/andrew_babo~cremyx-diarize/runs": { "post": { "operationId": "runs-sync-andrew_babo-cremyx-diarize", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/andrew_babo~cremyx-diarize/run-sync": { "post": { "operationId": "run-sync-andrew_babo-cremyx-diarize", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "op": { "title": "Operation", "enum": [ "diarize", "capabilities" ], "type": "string", "description": "Diarize speakers, or return supported capabilities.", "default": "diarize" }, "source": { "title": "Audio or video source", "type": "string", "description": "https:// URL, or kv:/ from an earlier run (e.g. the audio16k.wav produced by cremyx-media-tools). Any format works — it is converted to 16 kHz mono internally." }, "transcript": { "title": "Transcript to label (optional)", "type": "string", "description": "https:// URL or kv:/ of a cremyx-asr transcript.json. When set, the actor also returns the same words/segments with a speaker label attached." }, "options": { "title": "Options", "type": "object", "description": "{ num_speakers, cluster_threshold, min_duration_on, min_duration_off, threads }. Set num_speakers when you know the exact count; otherwise clustering uses cluster_threshold (default 0.5). Sharding: start_sec, duration_sec, overlap_sec — diarize only that window; turns are offset back to the original timeline, items past duration_sec flagged _overlap. Speaker IDs are only consistent within one run/shard." }, "output": { "title": "Output", "type": "object", "description": "{ signed_upload_url } to PUT diarization.json straight into your own storage." }, "cleanup": { "title": "Cleanup policy", "enum": [ "on_success", "always", "off" ], "type": "string", "description": "on_success = keep only result artifacts in the run's key-value store. always = also drop them after the signed upload. off = keep everything for debugging.", "default": "on_success" }, "callback": { "title": "Completion webhook", "type": "object", "description": "{ url, secret_header: { name, value } } — POSTed with the result JSON when the run finishes." } } }, "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 } } } } } } } } } }