aid: uberduck
url: https://raw.githubusercontent.com/api-evangelist/uberduck/refs/heads/main/apis.yml
name: Uberduck
kind: company
description: >-
  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.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- Text to Speech
- TTS
- Voice
- Voice Cloning
- Speech Synthesis
- Conversational AI
created: '2026-07-11'
modified: '2026-07-11'
specificationVersion: '0.19'
apis:
- aid: uberduck:uberduck-text-to-speech-api
  name: Uberduck Text-to-Speech API
  tags:
  - Text to Speech
  - TTS
  - Speech Synthesis
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uberduck.ai/api-reference/text-to-speech-v-1-text-to-speech-post
  baseURL: https://api.uberduck.ai/v1
  properties:
  - url: https://docs.uberduck.ai/guides/text-to-speech
    type: Documentation
  - url: https://docs.uberduck.ai/api-reference/text-to-speech-v-1-text-to-speech-post
    type: APIReference
  - url: openapi/uberduck-openapi.yml
    type: OpenAPI
  - url: collections/uberduck.postman_collection.json
    type: PostmanCollection
  - url: collections/uberduck.opencollection.json
    type: OpenCollection
  description: >-
    Convert up to 10,000 characters of text into speech with a chosen voice and
    model via POST /v1/text-to-speech. Supports common and model-specific
    parameters and a selectable output format (mp3, wav, etc.); returns a URL to
    the generated audio.
- aid: uberduck:uberduck-voices-api
  name: Uberduck Voices API
  tags:
  - Voices
  - Voice Cloning
  - Catalog
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uberduck.ai/guides/voice-selection
  baseURL: https://api.uberduck.ai/v1
  properties:
  - url: https://docs.uberduck.ai/guides/voice-selection
    type: Documentation
  - url: https://docs.uberduck.ai/api-reference/endpoints/models
    type: APIReference
  - url: openapi/uberduck-openapi.yml
    type: OpenAPI
  - url: collections/uberduck.postman_collection.json
    type: PostmanCollection
  - url: collections/uberduck.opencollection.json
    type: OpenCollection
  description: >-
    List and filter available voices (GET /v1/voices) by age, gender, accent,
    mood, style, language, model, name, tag, or free-text search with
    pagination, and create instant zero-shot voice clones from reference audio
    (POST /v1/voices).
- aid: uberduck:uberduck-models-api
  name: Uberduck Models API
  tags:
  - Models
  - Providers
  - Catalog
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uberduck.ai/api-reference/endpoints/models
  baseURL: https://api.uberduck.ai/v1
  properties:
  - url: https://docs.uberduck.ai/api-reference/endpoints/models
    type: APIReference
  - url: openapi/uberduck-openapi.yml
    type: OpenAPI
  - url: collections/uberduck.postman_collection.json
    type: PostmanCollection
  - url: collections/uberduck.opencollection.json
    type: OpenCollection
  description: >-
    List the text-to-speech models available on Uberduck (GET /v1/models),
    optionally filtered by provider such as aws, google, or azure, with metadata
    including provider, description, features, and whether a model is default or
    open source.
- aid: uberduck:uberduck-conversational-voice-api
  name: Uberduck Conversational Voice API
  tags:
  - Conversational AI
  - Voice Agents
  - LiveKit
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uberduck.ai/api-reference/uberduck-text-to-speech-api
  baseURL: https://api.uberduck.ai/v1
  properties:
  - url: https://docs.uberduck.ai/api-reference/uberduck-text-to-speech-api
    type: APIReference
  - url: openapi/uberduck-openapi.yml
    type: OpenAPI
  - url: collections/uberduck.postman_collection.json
    type: PostmanCollection
  - url: collections/uberduck.opencollection.json
    type: OpenCollection
  description: >-
    Mint a LiveKit token for a real-time AI voice call (POST
    /v1/conversational/token). Returns the LiveKit server URL, a room name, and
    a JWT participant token used to join the call. The realtime media transport
    is provided by LiveKit (WebRTC), not by Uberduck's own HTTP API.
common:
- type: DomainSecurity
  url: security/uberduck-domain-security.yml
- type: Authentication
  url: authentication/uberduck-authentication.yml
- type: LinkedIn
  url: https://www.linkedin.com/company/uberduck-ai
- type: Website
  url: https://uberduck.ai
- type: Documentation
  url: https://docs.uberduck.ai
- type: APIReference
  url: https://api.uberduck.ai/docs
- type: Plans
  url: plans/uberduck-plans-pricing.yml
- type: RateLimits
  url: rate-limits/uberduck-rate-limits.yml
- type: FinOps
  url: finops/uberduck-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com