{ "openapi": "3.0.1", "info": { "title": "Voice Match — speaker similarity & TTS consistency", "description": "Compare a reference voice against one or more audios and get a similarity score + same/different-voice decision. Built for TTS consistency QC: generate several takes, keep the ones that match. ECAPA-TDNN, CPU, no GPU, no key.", "version": "0.1", "x-build-id": "yv30kqur9ItZmBJUr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/synthetic.ia~voice-match/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-synthetic.ia-voice-match", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/synthetic.ia~voice-match/runs": { "post": { "operationId": "runs-sync-synthetic.ia-voice-match", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/synthetic.ia~voice-match/run-sync": { "post": { "operationId": "run-sync-synthetic.ia-voice-match", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "referenceAudio", "candidateAudios" ], "properties": { "referenceAudio": { "title": "Reference audio", "type": "string", "description": "The known voice that everything is compared against. An http(s) URL or base64. About 5–10 seconds of clean speech works best.", "default": "https://raw.githubusercontent.com/speechbrain/speechbrain/develop/tests/samples/ASR/spk1_snt1.wav" }, "candidateAudios": { "title": "Audios to compare", "type": "array", "description": "One or more audios to check against the reference (e.g. your other TTS takes). URLs or base64. The example compares one clip of the same speaker (match) and one of a different speaker (no match).", "default": [ "https://raw.githubusercontent.com/speechbrain/speechbrain/develop/tests/samples/ASR/spk1_snt2.wav", "https://raw.githubusercontent.com/speechbrain/speechbrain/develop/tests/samples/ASR/spk2_snt1.wav" ], "items": { "type": "string" } }, "level": { "title": "Strictness", "enum": [ "strict", "tts", "balanced", "tolerant" ], "type": "string", "description": "How close the voices must be to count as the same. 'TTS' = same synthetic voice across takes (strict). 'Tolerant' = noisy/phone audio. You always get the raw score too.", "default": "tts" }, "detectAi": { "title": "Also flag AI / deepfake voices", "type": "boolean", "description": "Adds an 'aiGenerated' confidence to every audio. Turn off if you only care about the voice match (a little faster).", "default": true }, "threshold": { "title": "Custom threshold", "minimum": 0, "maximum": 100, "type": "integer", "description": "Use your own cut-off instead of the Strictness preset: cosine similarity × 100 (e.g. 70 = 0.70). Leave empty to use the preset." } } }, "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 } } } } } } } } } }