XiaoZhan AIhubXiaoZhan AIhub
HomeAI ChatAgentsCreateDigital HumansCreative AgentModel catalogueMarketTopicsPriceDocs
XiaoZhan AIhubXiaoZhan AIhub
HomeAI ChatAgentsCreateDigital HumansCreative AgentModel catalogueMarketTopicsPriceDocs
Model catalogueVoice Cloning · Create a Voice
O

Voice Cloning · Create a Voice

NEW

Model ID

Put this value in the request body's `model` field — not the display name above.

AudioClosed source

by other · Voice cloning: upload or record your own (or an authorised) voice to clone a reusable voice of your own for speech synthesis and avatar voice-overs.

Try it now

Quick start

EndpointPOST /v1/audio/voices
AuthenticationAuthorization: Bearer sk-gpushare-…Get API key
Call styleAsynchronous: submit for an ID, then poll until it settles
Base URLhttps://api.dflop.top/v1
① Submit the clone · cURL
curl https://api.dflop.top/v1/audio/voices \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "我的音色",
    "audio_url": "https://example.com/sample.mp3",
    "async": true
  }'
# 参考音频:公网直链,5 秒-3 分钟清晰人声
# ⚠️ 克隆真实人声前请确认已获得声音所有者授权
② Poll until ready, then use it for synthesis · cURL
curl https://api.dflop.top/v1/audio/voices/$VOICE_ID \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx"
# status: pending / ready / failed(失败自动全额退款)
# ready 后把这个 id 传进 /v1/audio/speech 的 voice 字段

This is an async task: submit for a task ID, then poll until it settles. Polling itself is free.

Pricing

Billed per call: a one-off training fee per cloned voice.

Rates
per clone 1,800Credits
  • Failed clones are refunded in full automatically.
  • Synthesizing speech with a cloned voice is billed separately at the text-to-speech per-character rate.
  • All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Sign in and any personal discount on your account will show up here. Sign in

Capabilities & specs

Category
Audio
Endpoint family
Voice cloning (Audio Voices)
Released
2026-07-24
License
Closed source

Try it

Models like this bill for real per image / per second / per call and are mostly async tasks, so there is no one-click test here. Use the sample code above, or generate in the matching workbench (which has a parameter panel and a cost estimate).

Open the workbench

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ Voice Cloning · Create a Voice→✓ voice-clone-pro

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

The reference audio is not a publicly reachable direct link, or its length is outside the 5-second to 3-minute range.

→ Check your request body against the sample code above

More models from this vendor

O
Smart editclip-compose
O
Digital human videodh-avatar
O
Create digital humandh-avatar-create
O
Text to speechvoice-tts-pro
O
xiaozhanAIxiaozhanAI
O
xiaozhanimagexiaozhanimage
Try it

Voice Cloning · Create a Voice FAQ

How do I call Voice Cloning · Create a Voice?
Set the model field of the request body to voice-clone-pro, send it to https://api.dflop.top/v1/audio/voices, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. This is not a chat SKU; submit tasks to the dedicated endpoint above.
How much does the Voice Cloning · Create a Voice API cost?
  • ·Per voice clone: 1,800 credits (≈ ¥30 / ≈ $4.45)
  • ·Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.

Markdown version of this page (Chinese): /models/voice-clone-pro.md