The Operations API from PyannoteAI — 3 operation(s) for operations.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/pyannoteai:pyannoteai-operations-api"curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: pyannoteAI Operations API
description: ''
version: local
contact: {}
termsOfService: https://pyannote.ai/terms-of-use
servers:
- url: https://api.pyannote.ai
tags:
- name: Operations
paths:
/v1/diarize:
post:
operationId: diarize
parameters: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/DiarizeRequest'
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/JobCreated'
'400':
description: Invalid request
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationErrorResponse'
'402':
description: Subscription is required
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'429':
description: Too many requests
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
security:
- api-key: []
summary: Diarize audio
tags:
- Operations
x-api-key-permissions:
- jobs:write
/v1/voiceprint:
post:
operationId: voiceprint
parameters: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/VoiceprintRequest'
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/JobCreated'
'400':
description: Invalid request
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationErrorResponse'
'402':
description: Subscription is required
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'429':
description: Too many requests
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
security:
- api-key: []
summary: Extract voiceprint
tags:
- Operations
x-api-key-permissions:
- jobs:write
/v1/identify:
post:
operationId: identify
parameters: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/IdentifyRequest'
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/JobCreated'
'400':
description: Invalid request
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationErrorResponse'
'402':
description: Subscription is required
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'429':
description: Too many requests
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
security:
- api-key: []
summary: Identify speaker with diarization
tags:
- Operations
x-api-key-permissions:
- jobs:write
components:
schemas:
IdentifyRequest:
type: object
properties:
url:
type: string
description: URL of the audio file to be processed
example: https://example.com/audio.wav
webhook:
type: string
description: Webhook URL to receive results when job is completed (optional)
example: https://example.com/webhook
webhookStatusOnly:
type: boolean
default: false
description: When true, webhook payload only includes jobId and status (excludes output). Useful for large payloads.
example: true
model:
type:
- string
- 'null'
enum:
- precision-2
example: precision-2
default: precision-2
numSpeakers:
type: number
minimum: 1
description: Number of speakers. Only use if the number of speakers is known in advance. Number of speakers is detected automatically if not provided. Setting this value results in better overall diarization performance. In rare cases where we cannot honor this request (e.g. short files and large number of speakers), a warning will be added to the output. Equivalent to sending minSpeakers==maxSpeakers
example: 2
minSpeakers:
type: number
minimum: 1
description: Minimum number of speakers (must be <= maxSpeakers if both are set)
example: 1
maxSpeakers:
type: number
minimum: 1
description: Maximum number of speakers (must be >= minSpeakers if both are set)
example: 4
turnLevelConfidence:
type:
- boolean
- 'null'
default: false
description: Includes turn-level confidence values in the output.
example: true
exclusive:
type: boolean
default: false
description: Includes exclusive diarization values in the output in `exclusiveDiarization` key (equivalent to diarization but without overlapping speech).
example: true
confidence:
type: boolean
default: false
description: Include confidence values in the output. Output is considerably larger when this option is enabled. Output includes a list of confidence scores with a resolution.
example: true
matching:
description: Customize how voiceprints are matched against speakers
allOf:
- $ref: '#/components/schemas/MatchingOptions'
voiceprints:
minItems: 1
maxItems: 50
description: List of voiceprints to identify against
type: array
items:
$ref: '#/components/schemas/Voiceprint'
required:
- voiceprints
JobCreated:
type: object
properties:
jobId:
type: string
example: 3c8a89a5-dcc6-4edb-a75d-ffd64739674d
description: ID of the job
status:
type: string
description: Status of the job
example: created
enum:
- pending
- created
- succeeded
- canceled
- failed
- running
warning:
type: string
description: Warning message if any
required:
- jobId
- status
MatchingOptions:
type: object
properties:
exclusive:
type:
- boolean
- 'null'
default: true
description: Prevent multiple speakers from being matched to the same voiceprint. Default to true
threshold:
type:
- number
- 'null'
default: 0
minimum: 0
maximum: 100
format: float
description: Prevent matching if confidence score is below this threshold. Value is between 0 and 100. Default is 0, meaning all voiceprints are matched
VoiceprintRequest:
type: object
properties:
url:
type: string
description: URL of the voiceprint audio file
example: https://example.com/voice.wav
model:
type:
- string
- 'null'
enum:
- precision-2
example: precision-2
default: precision-2
webhook:
type: string
description: Webhook URL to receive voiceprint results (optional)
example: https://example.com/webhook
webhookStatusOnly:
type: boolean
default: false
description: When true, webhook payload only includes jobId and status (excludes output). Useful for large payloads.
example: true
required:
- url
ValidationErrorResponse:
type: object
properties:
message:
type: string
description: Error message
example: Invalid request
errors:
description: List of errors
type: array
items:
$ref: '#/components/schemas/ValidationError'
required:
- message
- errors
Voiceprint:
type: object
properties:
label:
type: string
maxLength: 100
pattern: ^(?!speaker_).*
description: Label for the speaker. Labels can't start with "SPEAKER_"
example: John Doe
voiceprint:
type: string
maxLength: 20000
format: string
description: Voiceprint of a speaker
example: U29tZUJhc2U2NERhdGE
required:
- label
- voiceprint
ApiError:
type: object
properties:
requestId:
type: string
description: Request ID
example: 37a4c3a0-b034-4e8c-9ed9-76da6645544a
message:
type: string
description: Error message
example: Error message
required:
- requestId
- message
ValidationError:
type: object
properties:
field:
type: string
description: Field name
example: url
message:
type: string
description: Error message
example: Invalid URL
required:
- field
- message
DiarizeRequest:
type: object
properties:
url:
type: string
description: URL of the audio file to be processed
example: https://example.com/audio.wav
webhook:
type: string
description: Webhook URL to receive results when job is completed (optional)
example: https://example.com/webhook
webhookStatusOnly:
type: boolean
default: false
description: When true, webhook payload only includes jobId and status (excludes output). Useful for large payloads.
example: true
model:
type:
- string
- 'null'
enum:
- precision-2
- community-1
example: precision-2
default: precision-2
numSpeakers:
type: number
minimum: 1
description: Number of speakers. Only use if the number of speakers is known in advance. Number of speakers is detected automatically if not provided. Setting this value results in better overall diarization performance. In rare cases where we cannot honor this request (e.g. short files and large number of speakers), a warning will be added to the output. Equivalent to sending minSpeakers==maxSpeakers
example: 2
minSpeakers:
type: number
minimum: 1
description: Minimum number of speakers (must be <= maxSpeakers if both are set)
example: 1
maxSpeakers:
type: number
minimum: 1
description: Maximum number of speakers (must be >= minSpeakers if both are set)
example: 4
turnLevelConfidence:
type:
- boolean
- 'null'
default: false
description: Includes turn-level confidence values in the output.
example: true
exclusive:
type: boolean
default: false
description: Includes exclusive diarization values in the output in `exclusiveDiarization` key (equivalent to diarization but without overlapping speech).
example: true
confidence:
type: boolean
default: false
description: Include confidence values in the output. Output is considerably larger when this option is enabled. Output includes a list of confidence scores with a resolution.
example: true
transcription:
type: boolean
default: false
description: Enable speaker attributed transcription. Only available for the `precision-2` diarization model.
transcriptionConfig:
description: 'Transcription configuration, if `transcription: true`'
allOf:
- $ref: '#/components/schemas/TranscriptionConfiguration'
required:
- url
TranscriptionConfiguration:
type: object
properties:
model:
type: string
default: parakeet-tdt-0.6b-v3
enum:
- parakeet-tdt-0.6b-v3
- faster-whisper-large-v3-turbo
description: "Transcription model to use. Supported languages depend on the chosen model:\n - `parakeet-tdt-0.6b-v3`: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Russian or Ukrainian.\n - `faster-whisper-large-v3-turbo`: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Cantonese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, HaitianCreole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Myanmar, Nepali, Norwegian, Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish or Yoruba."
example: faster-whisper-large-v3-turbo
securitySchemes:
api-key:
scheme: bearer
bearerFormat: JWT
type: http
externalDocs:
description: pyannoteAI Docs
url: https://docs.pyannote.ai/