D-ID Talks API

openapi: 3.0.3
info:
  title: D-ID Agents Talks API
  description: 'API for creating and managing interactive real-time AI agents that combine digital avatar streaming with large language models, RAG-based knowledge bases, and custom tools. Supports WebRTC and LiveKit-powered streaming sessions, conversation memory, chat export, and integration with third-party LLM providers. Enables face-to-face AI conversations at scale.

    '
  version: 1.0.0
  contact:
    url: https://www.d-id.com
  termsOfService: https://www.d-id.com/terms-of-use/
servers:
- url: https://api.d-id.com
  description: D-ID Production API
security:
- basicAuth: []
- bearerAuth: []
tags:
- name: Talks
  description: Generate AI talking-head videos (V2 Photo / V3 Pro avatars)
paths:
  /talks:
    get:
      operationId: gettalks
      summary: List talks
      description: Retrieve a paginated list of talks for the authenticated user.
      tags:
      - Talks
      parameters:
      - name: limit
        in: query
        description: Number of talks to return (default 100).
        schema:
          type: number
          default: 100
      - name: token
        in: query
        description: Pagination token from a previous response.
        schema:
          type: string
      responses:
        '200':
          description: Paginated list of talks.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetTalksDto'
        '401':
          $ref: '#/components/responses/Unauthorized'
    post:
      operationId: createtalk
      summary: Create a talk
      description: 'Generate an AI talking-head video by combining a source image with a text script or audio file. Processing is asynchronous — poll GET /talks/{id} or provide a webhook URL for completion notification.

        '
      tags:
      - Talks
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateTalkDto'
      responses:
        '201':
          description: Talk created and queued for processing.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TalkResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '403':
          $ref: '#/components/responses/Forbidden'
        '451':
          $ref: '#/components/responses/ContentModeration'
  /talks/{id}:
    get:
      operationId: gettalk
      summary: Get a talk
      description: Retrieve the status and result of a specific talk.
      tags:
      - Talks
      parameters:
      - $ref: '#/components/parameters/resourceId'
      responses:
        '200':
          description: Talk object.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetTalkDto'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
    delete:
      operationId: deletetalk
      summary: Delete a talk
      description: Delete a specific talk by ID. Cannot delete a talk that is currently processing.
      tags:
      - Talks
      parameters:
      - $ref: '#/components/parameters/resourceId'
      responses:
        '200':
          description: Deleted talk object.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetTalkDto'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
        '409':
          description: Talk is in process, try again later.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JsonError'
components:
  responses:
    PaymentRequired:
      description: Insufficient credits.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/JsonError'
    BadRequest:
      description: Bad request — invalid parameters.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/JsonError'
    Unauthorized:
      description: Authentication failure.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/JsonError'
          example:
            kind: AuthorizationError
            description: user unauthenticated
    NotFound:
      description: Resource not found.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/JsonError'
          example:
            kind: NotFoundError
            description: not found
    Forbidden:
      description: Permission denied.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/JsonError'
    ContentModeration:
      description: Content moderation rejection.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/JsonError'
  schemas:
    Script:
      oneOf:
      - $ref: '#/components/schemas/TextScript'
      - $ref: '#/components/schemas/AudioScript'
      discriminator:
        propertyName: type
    GetTalkDto:
      type: object
      properties:
        id:
          type: string
          description: Unique talk identifier.
        user_id:
          type: string
          description: User who submitted the talk.
        source_url:
          type: string
          format: uri
          description: Source image URL (.jpg or .png).
        audio_url:
          type: string
          format: uri
          description: Audio file URL used for the actor.
        created_at:
          type: string
          format: date-time
        created_by:
          type: string
        started_at:
          type: string
          format: date-time
        modified_at:
          type: string
          format: date-time
        status:
          $ref: '#/components/schemas/TalkStatus'
        result_url:
          type: string
          format: uri
          description: S3 URI to the resulting video.
        config:
          type: object
          description: Configuration used for processing.
        webhook:
          type: string
          format: uri
        metadata:
          type: object
          description: Collected process data.
    TalkStatus:
      type: string
      enum:
      - created
      - started
      - done
      - error
      - rejected
      description: Processing status of a talk or video job.
    JsonError:
      type: object
      properties:
        kind:
          type: string
          description: Error type identifier.
          example: AuthorizationError
        description:
          type: string
          description: Human-readable error description.
          example: user unauthenticated
    TalkResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: talk
        created_at:
          type: string
          format: date-time
        created_by:
          type: string
        status:
          $ref: '#/components/schemas/TalkStatus'
    TextScript:
      type: object
      required:
      - type
      - input
      properties:
        type:
          type: string
          enum:
          - text
        input:
          type: string
          description: Text content to synthesize (3–40,000 characters).
          minLength: 3
          maxLength: 40000
        provider:
          type: object
          description: TTS provider configuration.
          properties:
            type:
              type: string
              enum:
              - microsoft
              - elevenlabs
              - amazon
              - google
              - azure-openai
            voice_id:
              type: string
              description: Voice identifier for the selected provider.
            language:
              type: string
              description: Language code for TTS synthesis.
    GetTalksDto:
      type: object
      properties:
        talks:
          type: array
          items:
            $ref: '#/components/schemas/GetTalkDto'
        token:
          type: string
          description: Pagination token for the next page.
    AudioScript:
      type: object
      required:
      - type
      - audio_url
      properties:
        type:
          type: string
          enum:
          - audio
        audio_url:
          type: string
          format: uri
          description: URL of the audio file (max 15 MB, 5–10 minutes duration).
    CreateTalkDto:
      type: object
      required:
      - script
      properties:
        source_url:
          type: string
          format: uri
          description: URL of the source image to animate (defaults to Alice demo image).
        script:
          $ref: '#/components/schemas/Script'
        config:
          type: object
          description: Advanced configuration options.
          properties:
            logo:
              type: object
              properties:
                url:
                  type: string
                  format: uri
                position:
                  type: array
                  items:
                    type: number
            result_format:
              type: string
              enum:
              - mp4
              - gif
              - wav
            fluent:
              type: boolean
            pad_audio:
              type: number
        user_data:
          type: string
          description: Custom metadata (max 1,000 characters).
          maxLength: 1000
        name:
          type: string
          description: Title for the generated video.
        webhook:
          type: string
          format: uri
          description: HTTPS webhook URL for completion notification.
        result_url:
          type: string
          format: uri
          description: Custom destination URL for the output video.
  parameters:
    resourceId:
      name: id
      in: path
      required: true
      description: Unique resource identifier.
      schema:
        type: string
  securitySchemes:
    basicAuth:
      type: http
      scheme: basic
      description: HTTP Basic Authentication using API key as username.
    bearerAuth:
      type: http
      scheme: bearer
      description: Bearer token authentication.
    clientKeyAuth:
      type: apiKey
      in: header
      name: Authorization
      description: Scoped client key for SDK embedding.
externalDocs:
  description: D-ID Agents API Reference
  url: https://docs.d-id.com/reference/agents