openapi: 3.2.0
info:
  description: The LocalAI Rest API.
  title: LocalAI Voice Recognition API
  contact:
    name: LocalAI
    url: https://localai.io
  license:
    name: MIT
    url: https://raw.githubusercontent.com/mudler/LocalAI/master/LICENSE
  version: 2.0.0
servers:
- url: /
tags:
- name: voice-recognition
paths:
  /v1/voice/analyze:
    post:
      tags:
      - voice-recognition
      summary: Analyze demographic attributes (age, gender, emotion) from a voice clip.
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.VoiceAnalyzeResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VoiceAnalyzeRequest'
        description: query params
        required: true
  /v1/voice/embed:
    post:
      tags:
      - voice-recognition
      summary: Extract a speaker embedding from an audio clip.
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.VoiceEmbedResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VoiceEmbedRequest'
        description: query params
        required: true
  /v1/voice/forget:
    post:
      tags:
      - voice-recognition
      summary: Remove a previously-registered speaker by ID.
      responses:
        '204':
          description: No Content
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VoiceForgetRequest'
        description: query params
        required: true
  /v1/voice/identify:
    post:
      tags:
      - voice-recognition
      summary: Identify a speaker against the registered database (1:N recognition).
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.VoiceIdentifyResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VoiceIdentifyRequest'
        description: query params
        required: true
  /v1/voice/register:
    post:
      tags:
      - voice-recognition
      summary: Register a speaker for 1:N identification.
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.VoiceRegisterResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VoiceRegisterRequest'
        description: query params
        required: true
  /v1/voice/verify:
    post:
      tags:
      - voice-recognition
      summary: Verify that two audio clips were spoken by the same person.
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.VoiceVerifyResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VoiceVerifyRequest'
        description: query params
        required: true
components:
  schemas:
    schema.VoiceIdentifyResponse:
      type: object
      properties:
        matches:
          type: array
          items:
            $ref: '#/components/schemas/schema.VoiceIdentifyMatch'
    schema.VoiceAnalyzeResponse:
      type: object
      properties:
        segments:
          type: array
          items:
            $ref: '#/components/schemas/schema.VoiceAnalysis'
    schema.VoiceIdentifyRequest:
      type: object
      properties:
        audio:
          type: string
        model:
          type: string
        store:
          type: string
        threshold:
          type: number
        top_k:
          type: integer
    schema.VoiceForgetRequest:
      type: object
      properties:
        id:
          type: string
        model:
          type: string
        store:
          type: string
    schema.VoiceVerifyRequest:
      type: object
      properties:
        anti_spoofing:
          type: boolean
        audio1:
          type: string
        audio2:
          type: string
        model:
          type: string
        threshold:
          type: number
    schema.VoiceAnalyzeRequest:
      type: object
      properties:
        actions:
          description: subset of {"age","gender","emotion"}
          type: array
          items:
            type: string
        audio:
          type: string
        model:
          type: string
    schema.VoiceEmbedResponse:
      type: object
      properties:
        dim:
          type: integer
        embedding:
          type: array
          items:
            type: number
        model:
          type: string
    schema.VoiceRegisterResponse:
      type: object
      properties:
        id:
          type: string
        name:
          type: string
        registered_at:
          type: string
    schema.VoiceVerifyResponse:
      type: object
      properties:
        confidence:
          type: number
        distance:
          type: number
        model:
          type: string
        processing_time_ms:
          type: number
        threshold:
          type: number
        verified:
          type: boolean
    schema.VoiceAnalysis:
      type: object
      properties:
        age:
          type: number
        dominant_emotion:
          type: string
        dominant_gender:
          type: string
        emotion:
          type: object
          additionalProperties:
            type: number
            format: float32
        end:
          type: number
        gender:
          type: object
          additionalProperties:
            type: number
            format: float32
        start:
          type: number
    schema.VoiceIdentifyMatch:
      type: object
      properties:
        confidence:
          type: number
        distance:
          type: number
        id:
          type: string
        labels:
          type: object
          additionalProperties:
            type: string
        match:
          type: boolean
        name:
          type: string
    schema.VoiceRegisterRequest:
      type: object
      properties:
        audio:
          type: string
        labels:
          type: object
          additionalProperties:
            type: string
        model:
          type: string
        name:
          type: string
        store:
          type: string
    schema.VoiceEmbedRequest:
      type: object
      properties:
        audio:
          type: string
        model:
          type: string
  securitySchemes:
    BearerAuth:
      type: apiKey
      name: Authorization
      in: header