KeyoAPI

Duix Avatar API — Audio+Video Driven Digital Human

Searching for a Duix Avatar API?

Duix-Avatar is a digital-human model on KeyoAPI, a prepaid AI API gateway: call it at POST /v1/async/videos/audio-video-to-video, billed at $0.00685 / second from the same balance that covers chat, vision, OCR and video models.

Listed price: $0.00685 / second · Live catalog: Model Square · Static list: pricing list.

Get API key Open Model Square Compare API prices

Overview

Searching for a Duix Avatar API or a hosted alternative to self-managed digital-human stacks? KeyoAPI exposes Duix-Avatar as an async talking-avatar API: feed a face video plus driving audio, get lip-sync and expressions back as a render job. This is the API path for product teams — not a consumer Duix app. Build the loop on one prepaid key: generate speech with CosyVoice3 / Qwen3-TTS / IndexTTS-2, then drive Duix-Avatar. Per-second pricing (~$0.00685) maps to output length; confirm on the full pricing list. Cap max duration, show queue ETA, and moderate deepfake abuse. Prefer InfiniteTalk when you start from a still photo plus audio. Endpoint: POST /v1/async/videos/audio-video-to-video with model=Duix-Avatar, then GET /v1/task/{id}. Hub page: the AI avatar video generator page.

How to call it

Base URL: https://www.keyoapi.xyz/v1

Endpoint: POST /v1/async/videos/audio-video-to-video

Model: model=Duix-Avatar

curl https://www.keyoapi.xyz/v1/async/videos/audio-video-to-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F model=Duix-Avatar \
  -F audio=@./voice.wav \
  -F video=@./face.mp4
# then: GET /v1/task/{id}

Auth uses the same Bearer API key as chat. Full notes: Keyo docs.

FAQ

What is the Duix Avatar API on Keyo?

Call model=Duix-Avatar on POST /v1/async/videos/audio-video-to-video with driving audio and a face video, then poll /v1/task/{id}. Hub: the AI avatar video generator page.

Is generation realtime?

Duix-Avatar runs as an async job—submit audio/video drivers, then fetch the rendered avatar clip.

How do I supply voice?

Generate speech with IndexTTS-2, CosyVoice3, or Qwen3-TTS (or upload audio), then drive Duix-Avatar for lip-sync and expressions.

Billing unit?

About $0.00685 per second of output—see the full pricing list.

Related models

InfiniteTalk API IndexTTS-2 API CosyVoice3 API Qwen3-TTS API

Guide for Duix-Avatar. Catalog: the pricing page · Rates: the full pricing list.