Speaker Diarization — who spoke when, with meeting notes
Pricing
Pay per event
Split any recording into speaker turns: transcript per speaker, talk-time stats, speaker-labelled SRT/VTT and ready-to-paste Markdown meeting notes. Whisper + voice clustering run inside the Actor — no API key. Failed or silent files are never billed.
You can access the Speaker Diarization — who spoke when, with meeting notes programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "DgEfSvdQU74QAKZMd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/amanatools~speaker-diarization/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-amanatools-speaker-diarization", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/amanatools~speaker-diarization/runs": { "post": { "operationId": "runs-sync-amanatools-speaker-diarization", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/amanatools~speaker-diarization/run-sync": { "post": { "operationId": "run-sync-amanatools-speaker-diarization", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "media_urls" ], "properties": { "media_urls": { "title": "Media URLs", "type": "array", "description": "Audio/video file URLs (mp3, m4a, wav, ogg, flac, mp4, webm, …). Up to 25 URLs per run. Note: social-platform pages (YouTube, TikTok, …) are not supported — send direct media files you have the right to process.", "items": { "type": "string" } }, "num_speakers": { "title": "Number of speakers", "minimum": 0, "maximum": 16, "type": "integer", "description": "How many people are in the recording, if you know. Leave at 0 to detect automatically.", "default": 0 }, "max_speakers": { "title": "Max speakers (auto-detect ceiling)", "minimum": 2, "maximum": 16, "type": "integer", "description": "Upper bound for automatic speaker detection. Only used when 'Number of speakers' is 0.", "default": 8 }, "model": { "title": "Model", "enum": [ "tiny", "base" ], "type": "string", "description": "Whisper model for the transcript. 'tiny' (default) is fastest and cheapest — good on clear speech; 'base' is more accurate for accents, other languages or noisy audio, about 2-3x slower (same price per minute, the run just takes longer).", "default": "tiny" }, "language": { "title": "Language", "type": "string", "description": "ISO code like 'en', 'ar', 'es', 'ru' — or 'auto' to detect. Setting it explicitly is slightly faster and more reliable for short clips.", "default": "auto" }, "vad_filter": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Voice-activity detection removes long silences before transcribing. Keep it on for meetings and interviews.", "default": true }, "max_minutes_per_file": { "title": "Max minutes per file", "minimum": 1, "maximum": 480, "type": "integer", "description": "Hard cap on processed audio per file — this is also your cost ceiling: max spend per file = $0.005 + $0.007 x this number. Longer recordings are processed up to the cap and flagged 'truncated'.", "default": 30 }, "include_failed_files": { "title": "Include failed files in the dataset", "type": "boolean", "description": "When on, files that could not be downloaded or decoded appear in the dataset as error rows (never billed). Turn off to keep the dataset clean.", "default": true } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Speaker Diarization — who spoke when, with meeting notes from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: