Tool · Talking Avatar

AI Talking Avatar

The Talking Avatar tool animates a single portrait so it speaks your audio, with natural head and facial movement. It is a quick way to make a presenter, a welcome message or a short explainer without filming.

What you provide	One portrait photo and an audio recording
What you get	A video of the person speaking your audio
Cost	3 credits per 5 seconds of audio
Limit	Up to 30 seconds of audio per clip
Plan needed	Any plan or pay-per-use credits

AI Talking Avatar in the studio.
⚡ Open it in the studio →
Free to sign up. Pay per use from 10 credits, or subscribe from $47/mo.

What a Clip Costs

Audio length	Credits
5 seconds	3
15 seconds	9
30 seconds (maximum)	18

Longer scripts: make several clips of up to 30 seconds and join them in your video editor. A failed generation is refunded automatically.

How It Works

Choose a portrait. Front-facing, well lit, face large in the frame. Avoid sunglasses, heavy shadows and group photos.

Add audio. Record your own voice or use a track you have rights to.

Generate. The face is animated to speak the audio.

Combine and publish. Add captions, music and cutaways in your editor.

Good Uses

Welcome and onboarding messages (see avatars for training videos)
Product and service explainers
Short social clips with a spoken hook
Multilingual versions of the same message, using different audio

Consent and Labelling

Use your own photo, or a photo of someone who has clearly agreed, and never make a real person say things they did not say. Label clips as AI-generated where required and as good practice.

Pricing in One Line

Credits cost about $0.52 each on Starter, $0.49 on Pro and $0.39 on Studio, and $0.46 to $0.60 when bought pay-per-use. New customers get 20% off their first card payment. One-time credits never expire, and unused subscription credits carry over. Full list: credit costs.

Frequently Asked Questions

How does a talking avatar work?

You supply a portrait and audio. The model animates the face and head so the person appears to speak the audio.

How much does it cost?

Three credits per 5 seconds of audio. A 15-second clip is 9 credits and the 30-second maximum is 18.

What photo works best?

A sharp, front-facing portrait with good light and a neutral expression. Blurry photos give blurry results.

How is this different from lip sync?

Lip sync re-animates the mouth in an existing video. Talking Avatar starts from a single still photo.

Can I use a celebrity or someone else’s photo?

No. Only use your own photo or one you have permission to use.

⚡ 20% Off Your First Card Payment

Try AI Talking Avatar on Your Own Project

Buy a small amount of credits with no subscription, or subscribe from $47/mo. New customers get 20% off their first card payment.

⚡ Open it in the studio →

20% off first card payment automatically · Plans from $47/mo · Or pay-per-use, no subscription