Uberduck Conversational API

Mint LiveKit tokens for real-time conversational AI voice calls.

Operations 1

POST /v1/conversational/token Generate Conversational Token #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • 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.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/uberduck-conversational-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API 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 Specification

uberduck-conversational-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Uberduck Text To Speech Conversational API
  description: The Uberduck API converts text to natural-sounding speech across a catalog of voices and provider-backed models (AWS Polly, Google Cloud, Azure), lists and filters those voices, creates instant zero-shot voice clones from reference audio, and mints short-lived LiveKit tokens for real-time conversational AI voice calls. All requests are HTTPS request/response and authenticate with a Bearer API key generated in the Uberduck account settings. API access is a paid feature available on the Creator plan and above. This document is transcribed from Uberduck's published OpenAPI (https://api.uberduck.ai/openapi.json, version 0.1.0) and its Swagger UI at https://api.uberduck.ai/docs.
  version: 0.1.0
  contact:
    name: Uberduck
    url: https://uberduck.ai
servers:
- url: https://api.uberduck.ai
  description: Uberduck production API
security:
- HTTPBearer: []
tags:
- name: Conversational
  description: Mint LiveKit tokens for real-time conversational AI voice calls.
paths:
  /v1/conversational/token:
    post:
      operationId: generateConversationalToken
      tags:
      - Conversational
      summary: Generate Conversational Token
      description: Generate a LiveKit token for a real-time AI voice call. Returns the LiveKit server URL, a room name, and a JWT participant token the client uses to join the room. The realtime media transport itself is provided by LiveKit (WebRTC), not by Uberduck's own HTTP API.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ConversationalTokenRequest'
      responses:
        '200':
          description: LiveKit connection details.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ConversationalTokenResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
        '500':
          description: Internal server error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    HTTPValidationError:
      type: object
      properties:
        detail:
          type: array
          items:
            $ref: '#/components/schemas/ValidationError'
    ErrorResponse:
      type: object
      description: API error response format.
      required:
      - error
      properties:
        error:
          $ref: '#/components/schemas/ErrorDetail'
    ValidationError:
      type: object
      required:
      - loc
      - msg
      - type
      properties:
        loc:
          type: array
          items:
            anyOf:
            - type: string
            - type: integer
        msg:
          type: string
        type:
          type: string
    ConversationalTokenResponse:
      type: object
      description: Response schema for LiveKit token generation.
      required:
      - server_url
      - room_name
      - participant_token
      properties:
        server_url:
          type: string
          description: LiveKit server URL.
        room_name:
          type: string
          description: Room name to join.
        participant_token:
          type: string
          description: JWT token for authentication.
    ErrorDetail:
      type: object
      description: Details for an API error.
      required:
      - code
      - message
      properties:
        code:
          type: string
        message:
          type: string
        details:
          type: object
    AppAgentConfig:
      type: object
      required:
      - app_id
      properties:
        app_id:
          type: string
          description: App ID.
        path:
          type: string
          default: agent.yaml
          description: Path to the app.
    AgentConfig:
      type: object
      properties:
        raw:
          type: string
          description: Raw agent configuration in YAML format.
        json:
          type: object
          description: Agent configuration as dictionary/JSON format.
        url:
          type: string
          description: URL that points to agent configuration in YAML format.
        app:
          $ref: '#/components/schemas/AppAgentConfig'
    ConversationalTokenRequest:
      type: object
      description: Request schema for generating a LiveKit token for AI voice calls.
      properties:
        agent_config:
          $ref: '#/components/schemas/AgentConfig'
        identity:
          type: string
          description: User identity (defaults to 'voice_assistant_user').
        metadata:
          type: object
          description: Additional metadata to include in the token.
  responses:
    BadRequest:
      description: Bad request.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    ValidationError:
      description: Validation error.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/HTTPValidationError'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer
      description: Bearer API key generated in Uberduck account settings under the API section.