HD Talking Photo
Lip Sync in 480p to 2K
Upload a photo and a voice track, choose a resolution from 480p to 2K, and get a video that speaks it. Cost: from 11 credits for 10 seconds of audio at 480p.
Trusted by 10,000+ creators worldwide
Sharp Enough to Publish
You pick the resolution, so a draft can be quick and the final can be crisp.
480p, 768p, 1080p or 2K
Four output sizes, so a quick draft and a sharp final come from the same photo and voice track.
Length Matches Your Audio
The video lasts exactly as long as the voice track you add, so there is nothing to trim afterwards.
Follow the Words
Switch on transcription and the audio is read first, so the lips follow the words more closely.
Repeatable With a Seed
Set a seed and run the same inputs again for a similar result you can compare.
Priced by Audio and Size
From 11 credits for 10 seconds of audio at 480p. You see the exact price before you run.
Checked Before You Pay
The photo is checked before any credits are charged, so a refused image costs nothing.
Three Steps to an HD Talking Photo
Photo, voice, resolution.
Add a Photo and a Voice Track
Voice tracks from 5 s to 120 s.
Pick the Resolution
Choose 480p for a quick check or step up to 1080p or 2K for the final version.
Generate and Download
Check the price, run it, and download the video from your History.
HD Talking Photo FAQ
What is the HD talking photo?+
It animates a still photo so the mouth and face follow a voice track you supply, and returns a video at the resolution you choose, from 480p up to 2K.
How does the HD talking photo differ from the basic talking photo?+
The basic talking photo is quick and simple. This one is for results you will publish: you choose the output resolution, can have the audio transcribed to guide the lips, and can pin a seed.
What does an HD talking photo cost?+
From 11 credits for 10 seconds of audio at 480p. Priced per second of audio and by resolution: the same 10 seconds cost 17 credits at 768p, 34 credits at 1080p and 67 credits at 2K. A 30-second track at 768p costs 60 credits. You see the exact price before you run.
How short or long can the voice track be?+
Voice tracks from 5 s to 120 s.
What shape can the photo be?+
Most portraits and landscape photos work. The photo should not be much wider or taller than it is square: the width divided by the height has to stay between 0.4 and 2.5.
What does Follow the words do?+
It reads the words in your audio first, so the lips follow them more closely. Leave it off and the lips follow the sound alone.
Do I need permission to use a photo?+
Yes. Use your own photo or one of a person who agreed. Running it takes an account with a verified email and credits; there is no anonymous generation. If a run fails on the provider side, the credits go back to your balance.
Do I need a subscription?+
No. You can pay as you go: credit packs are one-time purchases and their credits never expire. If you would rather have a steady supply, the monthly Starter ($7.99), Creator ($19) and Pro ($49) plans refill your credits each month, and you can cancel anytime. Unused monthly credits do not roll over.