Uberduck

Uberduck is an AI voice platform whose public REST API converts text into 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 LiveKit tokens for real-time conversational AI voice calls. The API is HTTPS request/response with Bearer API-key authentication. It is self-serve but gated behind a paid plan - API access is a feature of the Creator plan and above. Uberduck's earlier AI music / rap-vocals API surface is no longer part of the published API; the current documented product (OpenAPI version 0.1.0) is focused on text-to-speech, voices, and conversational voice.

4 APIs 0 Features

AIText to SpeechTTSVoiceVoice CloningSpeech SynthesisConversational AI

Sources

opencollection: 1.0.0
info:
  name: Uberduck Text To Speech API
  version: 0.1.0
request:
  auth:
    type: bearer
    token: '{{apiKey}}'
items:
- info:
    name: Text-to-Speech
    type: folder
  items:
  - info:
      name: Text To Speech
      type: http
    http:
      method: POST
      url: https://api.uberduck.ai/v1/text-to-speech
      body:
        type: json
        data: "{\n  \"text\": \"Hello world! This is my first Uberduck API request.\",\n  \"voice\": \"polly_joanna\",\n \
          \ \"model\": \"polly_neural\",\n  \"output_format\": \"mp3\"\n}"
    docs: Convert up to 10,000 characters of text to speech with a chosen voice and model. Returns a URL to the generated
      audio.
- info:
    name: Voices
    type: folder
  items:
  - info:
      name: Get Voices
      type: http
    http:
      method: GET
      url: https://api.uberduck.ai/v1/voices
      params:
      - name: gender
        value: female
        type: query
        description: Filter by gender.
      - name: language
        value: en
        type: query
        description: Filter by language.
      - name: limit
        value: '20'
        type: query
        description: Page size.
      - name: offset
        value: '0'
        type: query
        description: Pagination offset.
    docs: List and filter available voices by age, gender, accent, mood, style, language, model, name, tag, or free-text search,
      with pagination.
  - info:
      name: Instant Voice Clone
      type: http
    http:
      method: POST
      url: https://api.uberduck.ai/v1/voices
      body:
        type: json
        data: "{\n  \"paths\": [\"/path/to/reference-audio.wav\"],\n  \"name\": \"My Cloned Voice\",\n  \"description\": \"\
          Zero-shot clone from a reference sample.\"\n}"
    docs: Create a zero-shot instant voice clone from one or more reference audio files. Returns the new voice's display name
      and UUID.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: Get Models
      type: http
    http:
      method: GET
      url: https://api.uberduck.ai/v1/models
      params:
      - name: provider
        value: aws
        type: query
        description: Filter by provider (aws, google, azure).
    docs: List available text-to-speech models, optionally filtered by provider.
- info:
    name: Conversational
    type: folder
  items:
  - info:
      name: Generate Conversational Token
      type: http
    http:
      method: POST
      url: https://api.uberduck.ai/v1/conversational/token
      body:
        type: json
        data: "{\n  \"identity\": \"voice_assistant_user\",\n  \"agent_config\": {\n    \"app\": { \"app_id\": \"your-app-id\"\
          , \"path\": \"agent.yaml\" }\n  }\n}"
    docs: Mint a LiveKit token for a real-time AI voice call. Returns the LiveKit server URL, room name, and JWT participant
      token. Realtime media flows over LiveKit (WebRTC).

Uberduck

APIs

Uberduck Text-to-Speech API

Uberduck Voices API

Uberduck Models API

Uberduck Conversational Voice API

Collections

Uberduck Text To Speech API

Pricing Plans

Uberduck Plans Pricing

Rate Limits

Uberduck Rate Limits

FinOps

Uberduck Finops

Resources

Sources