MixVoice API Overview

One unified HTTP API for AI Audio, AI Image and AI Video generation

Introduction

The MixVoice API lets you integrate AI Audio, AI Image and AI Video generation into any application through a single, unified HTTP interface. Every endpoint is authenticated with an API key (Authorization: Bearer <api_key>) and returns standard JSON. Most generation endpoints are asynchronous tasks: you submit a request, get back a task_id, then poll for the result.

  • Unified auth — one API key for every capability
  • Async task model — submit → poll → get the result URL
  • Usage-based billing — per character / per second / fixed credits, with automatic refunds on failure
  • Hosted results — generated audio/image/video is returned as a ready-to-download URL

Base URL: https://api.aiclonevoicefree.com Every path is prefixed with it, e.g. POST https://api.aiclonevoicefree.com/api/v2/voice/clone

Capabilities

Quickstart: AI voice cloning (3 steps)

# 1) Submit a voice-clone task with a reference audio + the text to synthesize; get a task_id
curl -X POST https://api.aiclonevoicefree.com/api/v2/voice/clone \
  -H "Authorization: Bearer sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello, this is speech cloned from my own voice.",
    "reference_audio_url": "https://oss.aiclonevoicefree.com/trump.wav",
    "model": "v1-real"
  }'
# → { "task_id": "xxxx", "status": "pending", "capability": "voice", "action": "clone", "created_at": 1780704348 }

# 2) Poll the status (one query endpoint shared by every capability)
curl https://api.aiclonevoicefree.com/api/v2/tasks/xxxx \
  -H "Authorization: Bearer sk_your_api_key"
# → { "status": "processing", ... }

# 3) Read audioUrl from the top level once completed
# → { "status": "completed", "audioUrl": "https://oss.aiclonevoicefree.com/tts/.../xxxx.wav", "providerUsed": "v1-async" }

Next steps

On this page