Make a photo talk

Use your own recording or make one in Text to Speech. The avatar model syncs the lips to the voice and adds natural blinks, nods and expressions, so one picture becomes a presenter.

Make a photo talk How it works

From 14 credits per 5 seconds of video
30 free credits when you sign up · no card needed
A run that fails is refunded automatically

Real output, made with Kling Avatar 2.0.

You add: A portrait and a voice recording
You get: A video of the portrait speaking
Starts at: 14 credits per 5 seconds of video

How it works

1
Upload a clear portrait with the face toward the camera.
2
Add the audio: a recording, or a voiceover from Text to Speech.
3
Generate. The video runs as long as your audio.

Make a photo talk

Tips for better results

A front-facing photo with the mouth visible gives the best lip sync.
Clean speech without music underneath syncs most accurately.
Add a short note on mood, like “calm and friendly”, to steer the expression.

Great for

Explainer and course videos
Social posts in a character’s voice
Personal video messages
UGC ads

Models you can use

2 models

PopNow starts you on Kling Avatar 2.0. Switch to another model in the generator any time; each one shows its price before you run it.

Questions people ask

Do I need to record my own voice?

No. Write a script in Text to Speech, pick a voice and use the result as the audio.

How long can the video be?

As long as your audio, within each model’s limit: up to a minute on the standard avatar and up to five minutes on Kling Avatar 2.0.

How is this different from Lip Sync?

Talking Avatar starts from a still photo and animates the whole head. Lip Sync starts from a video and changes only the mouth.

How much does Talking Avatar cost?

Talking Avatar starts at 14 credits per 5 seconds of video. The generator shows the exact price before you run it, and a run that fails is refunded automatically. New accounts get 30 free credits, enough to try it.