Upload a portrait
Shoulders up, neutral expression.
VideoVendor content policy appliesEarly access
数字人口播
One photo. One voice. A presenter.
A portrait and an audio file become a presenter: head movement, blinks, gestures and lip-sync are all driven by the sound. For product clips, intros, or characters who need to speak to camera.
一张脸、一段音频，出一个会说话的人。
Talking avatar
from $0.072/secDrop a face and an audio track hereor click to choose filesFiles stay in your project. Nothing is trained on.
length
frame
Invite code opens this tool in Chat. No code yet? Join the waitlist — we open the most-requested tools first.
Open in Chat
How it works
Three moves.
Upload audio
Clean voice, little background noise.
Run
Pick a calmer or livelier gesture style if offered.
You give
Inputs.
- One portrait
- Audio (speech or singing)
- Optional gesture style
You get
Outputs.
- Talking-head clip, audio embedded
Under the hood
Models behind this tool.
Each model lists its own price and content policy. The spicy route is MiniMax H3; other models follow their vendor’s rules.
FAQ
Short answers.
How long can the audio be?
Typically up to 30–60 seconds per run depending on the model; chain runs for longer scripts.
Can the avatar be a synthetic character?
Yes — generate the portrait with a text-to-image model first.
Is this spicy-route?
No. Avatar models apply their vendor policy; keep the content within it.
How do I get access?
Enter an invite code to open the tool in Chat, or join the waitlist from this page. We open seats in batches and prioritise the tools people ask for most.
Related tools