Azure AI Speech Models API
The Models API from Azure AI Speech — 2 operation(s) for models.
The Models API from Azure AI Speech — 2 operation(s) for models.
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/azure-ai-speech:azure-ai-speech-models-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
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: Custom voice Models API
version: '2026-01-01'
description: Custom voice API to create and deploy your voice.
x-typespec-generated:
- emitter: '@azure-tools/typespec-autorest'
security:
- ApiKeyAuth: []
- OAuth2Auth:
- https://cognitiveservices.azure.com/.default
tags:
- name: Models
paths:
/models:
get:
operationId: Models_List
description: Gets the list of models for the authenticated Speech service resource.
parameters:
- $ref: '#/components/parameters/Azure.Core.Foundations.ApiVersionParameter'
- $ref: '#/components/parameters/CustomListQueryParameters.skip'
- $ref: '#/components/parameters/CustomListQueryParameters.maxpagesize'
- $ref: '#/components/parameters/CustomListQueryParameters.filter'
responses:
'200':
description: The request has succeeded.
content:
application/json:
schema:
$ref: '#/components/schemas/PagedModel'
default:
description: An unexpected error response.
headers:
x-ms-error-code:
description: String error code indicating what went wrong.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/Azure.Core.Foundations.ErrorResponse'
x-ms-examples:
Get all models:
$ref: ./examples/get_models.json
x-ms-pageable:
nextLinkName: nextLink
tags:
- Models
summary: Models list
x-summary-source: derived
/models/{id}:
get:
operationId: Models_Get
description: Gets the model identified by the given ID.
parameters:
- $ref: '#/components/parameters/Azure.Core.Foundations.ApiVersionParameter'
- name: id
in: path
description: Resource id
required: true
schema:
type: string
maxLength: 64
minLength: 3
pattern: ^[a-zA-Z0-9][a-zA-Z0-9._-]{1,62}[a-zA-Z0-9]$
responses:
'200':
description: The request has succeeded.
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
default:
description: An unexpected error response.
headers:
x-ms-error-code:
description: String error code indicating what went wrong.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/Azure.Core.Foundations.ErrorResponse'
x-ms-examples:
Get a model:
$ref: ./examples/get_model.json
tags:
- Models
summary: Models get
x-summary-source: derived
put:
operationId: Models_Create
description: Creates a new voice model.
parameters:
- $ref: '#/components/parameters/Azure.Core.Foundations.ApiVersionParameter'
- name: id
in: path
description: Resource id
required: true
schema:
type: string
maxLength: 64
minLength: 3
pattern: ^[a-zA-Z0-9][a-zA-Z0-9._-]{1,62}[a-zA-Z0-9]$
- $ref: '#/components/parameters/OperationIdHeader'
responses:
'200':
description: The request has succeeded.
headers:
Operation-Location:
description: The location for monitoring the operation state.
schema:
type: string
format: uri
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
'201':
description: The request has succeeded and a new resource has been created as a result.
headers:
Operation-Location:
description: The location for monitoring the operation state.
schema:
type: string
format: uri
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
default:
description: An unexpected error response.
headers:
x-ms-error-code:
description: String error code indicating what went wrong.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/Azure.Core.Foundations.ErrorResponse'
x-ms-examples:
Create a model:
$ref: ./examples/create_model.json
Create a multi style model:
$ref: ./examples/create_multi_style_model.json
x-ms-long-running-operation-options:
final-state-via: original-uri
x-ms-long-running-operation: true
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
description: The resource instance.
required: true
tags:
- Models
summary: Models create
x-summary-source: derived
delete:
operationId: Models_Delete
description: Deletes the model identified by the given ID.
parameters:
- $ref: '#/components/parameters/Azure.Core.Foundations.ApiVersionParameter'
- name: id
in: path
description: Resource id
required: true
schema:
type: string
maxLength: 64
minLength: 3
pattern: ^[a-zA-Z0-9][a-zA-Z0-9._-]{1,62}[a-zA-Z0-9]$
responses:
'204':
description: 'There is no content to send for this request, but the headers may be useful. '
default:
description: An unexpected error response.
headers:
x-ms-error-code:
description: String error code indicating what went wrong.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/Azure.Core.Foundations.ErrorResponse'
x-ms-examples:
Delete a model:
$ref: ./examples/delete_model.json
tags:
- Models
summary: Models delete
x-summary-source: derived
components:
schemas:
resourceId:
type: string
description: Resource ID
minLength: 3
maxLength: 64
pattern: ^[a-zA-Z0-9][a-zA-Z0-9._-]{1,62}[a-zA-Z0-9]$
PagedModel:
type: object
description: Paged collection of Model items
properties:
value:
type: array
description: The Model items on this page
items:
$ref: '#/components/schemas/Model'
nextLink:
type: string
format: uri
description: The link to the next page of items
required:
- value
Azure.Core.Foundations.InnerError:
type: object
description: An object containing more specific information about the error. As per Azure REST API guidelines - https://aka.ms/AzureRestApiGuidelines#handling-errors.
properties:
code:
type: string
description: One of a server-defined set of error codes.
innererror:
$ref: '#/components/schemas/Azure.Core.Foundations.InnerError'
description: Inner error.
ModelProperties:
type: object
description: Model properties
properties:
presetStyles:
type: array
description: Preset styles of this model.
items:
type: string
styleTrainingSetIds:
type: object
description: Customized styles and associated training sets.
additionalProperties:
type: string
voiceStyles:
type: array
description: All styles supported by this model.
items:
type: string
readOnly: true
failureReason:
$ref: '#/components/schemas/ModelFailureReason'
description: Model training failure reason
failedTrainingsets:
type: array
description: IDs of failed training sets.
items:
type: string
readOnly: true
secondaryLocales:
type: array
description: Secondary locales that this model can speak. Locale code follows BCP-47.
items:
type: string
readOnly: true
PresetStyleItem:
type: object
description: 'Preset styles supported by the recipe. The voice model can support these styles
without any style training set.'
properties:
male:
type: array
description: Preset styles supported on male voice model.
items:
type: string
female:
type: array
description: Preset styles supported on female voice model.
items:
type: string
Model:
type: object
description: Model object
properties:
id:
$ref: '#/components/schemas/resourceId'
description: Resource id
readOnly: true
voiceName:
type: string
description: Voice name
minLength: 1
description:
type: string
description: Model description
recipe:
$ref: '#/components/schemas/Recipe'
description: Recipe for model building. Different recipes have different capability.
locale:
type: string
description: 'The locale of this model. Locale code follows BCP-47. You can find the text to
speech locale list here
https://learn.microsoft.com/azure/ai-services/speech-service/language-support?tabs=tts.'
projectId:
$ref: '#/components/schemas/resourceId'
description: Resource id
consentId:
$ref: '#/components/schemas/resourceId'
description: Resource id
trainingSetId:
$ref: '#/components/schemas/resourceId'
description: Resource id
engineVersion:
type: string
description: Engine version. Update this version can get the latest pronunciation bug fixing.
readOnly: true
properties:
$ref: '#/components/schemas/ModelProperties'
description: Model properties
status:
$ref: '#/components/schemas/Status'
description: Status of a resource.
createdDateTime:
type: string
format: date-time
description: 'The timestamp when the object was created. The timestamp is encoded as ISO 8601
date and time format ("YYYY-MM-DDThh:mm:ssZ", see
https://en.wikipedia.org/wiki/ISO_8601#Combined_date_and_time_representations).'
readOnly: true
lastActionDateTime:
type: string
format: date-time
description: 'The timestamp when the current status was entered. The timestamp is encoded as
ISO 8601 date and time format ("YYYY-MM-DDThh:mm:ssZ", see
https://en.wikipedia.org/wiki/ISO_8601#Combined_date_and_time_representations).'
readOnly: true
required:
- id
- recipe
- projectId
- consentId
- trainingSetId
ModelFailureReason:
type: string
description: Model training failure reason
enum:
- InaccessibleCustomerStorage
- SpeakerVerificationFailed
- TerminateByUser
- Internal
- DataNotReady
- DataNotEnough
x-ms-enum:
name: ModelFailureReason
modelAsString: true
values:
- name: InaccessibleCustomerStorage
value: InaccessibleCustomerStorage
description: 'The customer uses Bring Your Own Storage in Speech Account. But the storage is
not accessible now. Please check
[doc](https://learn.microsoft.com/azure/ai-services/speech-service/bring-your-own-storage-speech-resource?tabs=portal#configure-byos-associated-storage-account).'
- name: SpeakerVerificationFailed
value: SpeakerVerificationFailed
description: The consent and training audio are not from the same speaker.
- name: TerminateByUser
value: TerminateByUser
description: The customer canceled model training.
- name: Internal
value: Internal
description: Custom Voice Service error.
- name: DataNotReady
value: DataNotReady
description: Training data is not ready for model training.
- name: DataNotEnough
value: DataNotEnough
description: Training data is not enough for model training.
Azure.Core.Foundations.Error:
type: object
description: The error object.
properties:
code:
type: string
description: One of a server-defined set of error codes.
message:
type: string
description: A human-readable representation of the error.
target:
type: string
description: The target of the error.
details:
type: array
description: An array of details about specific errors that led to this reported error.
items:
$ref: '#/components/schemas/Azure.Core.Foundations.Error'
innererror:
$ref: '#/components/schemas/Azure.Core.Foundations.InnerError'
description: An object containing more specific information than the current object about the error.
required:
- code
- message
Recipe:
type: object
description: Recipe for model building. Different recipes have different capability.
properties:
kind:
type: string
description: Recipe kind
version:
type: string
description: Recipe version
description:
type: string
description: Recipe description
readOnly: true
minUtteranceCount:
type: integer
format: int32
description: Minimum utterance count required to train a voice model with this recipe.
readOnly: true
minStyleUtteranceCount:
type: integer
format: int32
description: Minimum utterance count required to train each customized style.
readOnly: true
maxCustomStyleNum:
type: integer
format: int32
description: Maximum customized style number supported in one voice model.
readOnly: true
datasetLocales:
type: array
description: 'The locale of the training dataset. Locale code follows BCP-47. You can find
the text to speech locale list here
https://learn.microsoft.com/azure/ai-services/speech-service/language-support?tabs=tts.'
items:
type: string
readOnly: true
modelLocales:
type: array
description: 'The locale that a voice model can speak with this recipe. Locale code follows
BCP-47. You can find the text to speech locale list here
https://learn.microsoft.com/azure/ai-services/speech-service/language-support?tabs=tts.'
items:
type: string
readOnly: true
presetStyles:
type: object
description: 'Preset styles supported by this recipe per locale. You can get these styles
without any style training set.'
additionalProperties:
$ref: '#/components/schemas/PresetStyleItem'
readOnly: true
minDurationInSeconds:
type: number
format: double
description: 'Minimum audio duration in seconds required to train a voice model with this
recipe.'
readOnly: true
Azure.Core.Foundations.ErrorResponse:
type: object
description: A response containing error details.
properties:
error:
$ref: '#/components/schemas/Azure.Core.Foundations.Error'
description: The error object.
required:
- error
Status:
type: string
description: Status of a resource.
enum:
- NotStarted
- Running
- Succeeded
- Failed
- Disabling
- Disabled
x-ms-enum:
name: Status
modelAsString: true
values:
- name: NotStarted
value: NotStarted
description: NotStarted
- name: Running
value: Running
description: Running
- name: Succeeded
value: Succeeded
description: Succeeded
- name: Failed
value: Failed
description: Failed
- name: Disabling
value: Disabling
description: Disabling
- name: Disabled
value: Disabled
description: Disabled
parameters:
CustomListQueryParameters.maxpagesize:
name: maxpagesize
in: query
description: The maximum number of items to include in a single response.
required: false
x-ms-parameter-location: method
schema:
type: integer
format: int32
default: 100
CustomListQueryParameters.filter:
name: filter
in: query
description: 'Filter condition.
- **Supported properties:** projectId, createdDateTime, locale, kind
- **Operators:**
- eq, ne are supported for all properties.
- gt, ge, lt, le are supported for createdDateTime.
- **Example:**
- ```filter=projectId eq ''Jessica''``` (filter by project ID)
- ```filter=kind eq ''ProfessionalVoice''``` (filter project by kind)
- ```filter=locale eq ''en-US''``` (filter training set and model by locale)
- ```filter=createdDateTime gt 2022-12-30T23:59:59.99Z``` (filter resource
created time after 2023-11-01)'
required: false
x-ms-parameter-location: method
schema:
type: string
OperationIdHeader:
name: Operation-Id
in: header
description: 'ID of the status monitor for the operation. If the Operation-Id header matches
an existing operation and the request is not identical to the prior request, it
will fail with a 400 Bad Request.'
required: false
x-ms-parameter-location: method
x-ms-client-name: operationId
schema:
type: string
maxLength: 64
minLength: 3
pattern: ^[a-zA-Z0-9][a-zA-Z0-9._-]{1,62}[a-zA-Z0-9]$
CustomListQueryParameters.skip:
name: skip
in: query
description: The number of result items to skip.
required: false
x-ms-parameter-location: method
schema:
type: integer
format: int32
default: 0
Azure.Core.Foundations.ApiVersionParameter:
name: api-version
in: query
description: The API version to use for this operation.
required: true
x-ms-parameter-location: method
x-ms-client-name: apiVersion
schema:
type: string
minLength: 1
securitySchemes:
ApiKeyAuth:
type: apiKey
name: Ocp-Apim-Subscription-Key
in: header
OAuth2Auth:
type: oauth2
flows:
implicit:
scopes:
https://cognitiveservices.azure.com/.default: ''
authorizationUrl: https://login.microsoftonline.com/common/oauth2/authorize
x-ms-parameterized-host:
hostTemplate: '{endpoint}/customvoice'
useSchemePrefix: false
parameters:
- name: endpoint
in: path
description: 'Supported Cognitive Services endpoints (protocol and hostname, for example:
https://eastus.api.cognitive.microsoft.com).'
required: true
type: string
format: uri
x-ms-skip-url-encoding: true