Make a video that speaks their language

Type the words in Spanish, French or German. A talking video says them, lip-synced.

Make my video

Cancel anytime · No watermark on any plan

Make a video that speaks their language

Type the words in Spanish, French or German. A talking video says them, lip-synced.

Cancel anytime · No watermark on any plan

AI Video Dubbing, Step by Step: From Upload to a Checked Export (2026)

Percify Team

Percify Team

Content Writer

June 17, 2026
3 min read

Made with Percify

Talking videos of you, from one photo

Quick Answer

AI video dubbing takes six steps. Clean up the source so one voice is clear. Decide whether the lips must match: ElevenLabs Dubbing keeps the speaker's voice without lip sync at 60 credits a minute on Percify, and HeyGen Video Translate resyncs the lips at 4 credits a second. Upload the video and set the source language, or Auto, and the target language. Have a native speaker check names, numbers and product terms. Fix any timing or mouth problems. Then label the result where the platform requires it.

The six steps of AI video dubbing, with the real settings: when the lips must match, which languages each model lists, what a 3 minute dub costs, what to check and how to label it. Checked 16 September 2026.

Related next steps

This is the procedure for dubbing an existing video into another language with AI, in order, with the settings the two dubbing models on Percify actually have, read on 16 September 2026. If you are translating a video of yourself and want the whole workflow including subtitles, see how to translate a video of yourself; if you are still choosing between dubbing, subtitles and re recording, see dub, subtitle or re record.

Your photo can say thisUpload one photo and type a line. A lip synced video of you.

Make this with your photo

The six steps

1. Prepare the source. Dubbing models separate the voice from everything else, so the cleaner the speech, the better the result. Remove music under the voice where you can, and cut long silences.

2. Decide whether the lips must match. This decides the model:

ElevenLabs DubbingHeyGen Video Translate
Keeps the speaker's voiceYesYes
Resyncs the lipsNoYes
Languages33 targets178 output options
Price on Percify60 credits a minute, 1 credit minimum4 credits a second (8 in precision mode), 8 minimum
A 3 minute video on Creator180 credits, about $3.80720 credits in 2 minute parts, about $15.18

A face that fills the frame needs the lips resynced; a screen recording, a voiceover or a small speaker does not.

3. Upload and set the languages. ElevenLabs Dubbing ↗ takes a video or an audio file, a source language (a list of 19 including Auto) and a target language from its 18. HeyGen Video Translate ↗ takes the video and one of 178 output languages. Nothing else needs setting.

4. Check the words with a native speaker. Names, numbers, prices, units and product terms are where machine translation fails quietly. Fix them before publishing, not after comments point them out.

5. Check timing and mouths. Translations run longer or shorter than the original, so watch for rushed or stretched lines. If you dubbed without lip sync and the face is prominent, either rerun with HeyGen Video Translate, or, for a talking head clip, make the dubbed audio speak from a photo with InfiniteTalk Fast ↗ at 2 credits a second. More fixes are in fixing AI dubbing.

6. Label and publish. TikTok requires a label ↗ on realistic AI content including AI generated speech, and in the EU Article 50 of the AI Act ↗ has required deepfakes to be disclosed since 2 August 2026. A dub in someone else's voice needs their written consent.

What a dub costs elsewhere

Per minute prices on other dubbing services, read on their own pricing pages, are compared in what AI dubbing costs. Every Percify plan has commercial rights and no watermark; Creator is $26 for 1,233 credits, and plans are on pricing.

Ready to Create Your Own AI Avatar?

Make a talking video of yourself from one photo, in your own voice. No watermark on any plan.

Get started

Cancel anytime from your profile

Got questions?

Frequently asked

Prepare clean speech, decide whether the lips must match, upload the video and set the source and target languages, have a native speaker check names, numbers and terms, fix timing and mouth problems, then label the result where the platform requires it.

On Percify both dubbing models keep the speaker's voice: ElevenLabs Dubbing at 60 credits a minute, and HeyGen Video Translate at 4 credits a second, which also resyncs the lips.

Only some tools do. ElevenLabs Dubbing changes the audio and leaves the mouth as it was; HeyGen Video Translate resyncs the lips. For a talking head clip you can also make the dubbed audio speak from a photo with InfiniteTalk Fast at 2 credits a second.

On Percify, 180 credits with ElevenLabs Dubbing, about $3.80 on the Creator plan, or 720 credits with HeyGen Video Translate in 2 minute parts, about $15.18, which includes lip sync. Checked 16 September 2026.

ElevenLabs Dubbing lists 33 target languages: Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, German, Greek, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tagalog, Tamil, Turkish, Ukrainian and Vietnamese. HeyGen Video Translate lists 178 output language options.

ai dubbingvideo translationlip synctutorialvoice
Percify Team
Published on
Share article

Related Reads

AI Video Dubbing: Real Costs and Render Times - Percify AI Avatar Blog Cover
AI Video Dubbing Tutorial Step By StepSep 2, 26

AI Video Dubbing: Real Costs and Render Times

Measured across 179 jobs: 480p fast runs 2 credits per second of audio, 720p costs three times that and takes almost four times longer.

Read Article
Percify Voice Studio: Clone a Voice, Then Dub - Percify AI Avatar Blog Cover
Percify Voice Studio / Clone Your Voice For Video / Ai Dubbing VoiceSep 5, 26

Percify Voice Studio: Clone a Voice, Then Dub

How voice cloning and dubbing actually work on Percify: the 5.6 second sample floor, 52 preset voices, what cloning costs, and the trap that breaks dubbed lip sync.

Read Article
Percify Avatar Studio: Talk From One Photo - Percify AI Avatar Blog Cover
Percify Avatar Studio / Talking Avatar From A Photo / How Long Should An Ai Avatar Video BeSep 5, 26

Percify Avatar Studio: Talk From One Photo

One photo and a script become a video of that face speaking. What 179 finished renders from 61 accounts say about the length, cost and framing that work.

Read Article
AI Lip Sync Software Compared - Percify AI Avatar Blog Cover
Lip Sync Software, Lip Sync Animation Software, Best Ai Lip Sync AppSep 2, 26

AI Lip Sync Software Compared

What decides lip sync quality, measured across 179 real renders: 720p takes 3.3x the render time of 480p fast, and 9 percent of failures are the source.

Read Article
Why AI Lip Sync Looks Wrong, and How to Fix It - Percify AI Avatar Blog Cover
How To Lip Sync / AI Animation Unnatural Stiff Limbs Bad Lip Sync TroubleshootingSep 2, 26

Why AI Lip Sync Looks Wrong, and How to Fix It

Nine percent of clips get retried on our platform, almost always for one of four reasons. How to tell which you have before spending credits again.

Read Article
7 AI Avatar Secrets for Snapchat Spotlight Success (2026 Fix) - Percify AI Avatar Blog Cover
Best Ai Avatar For Snapchat SpotlightJul 4, 26

7 AI Avatar Secrets for Snapchat Spotlight Success (2026 Fix)

How to get lip sync and voice right on an AI avatar for Snapchat Spotlight in 2026: the tools creators use and the settings that make clips look natural.

Read Article

Make your first talking video

One photo and a script is all it takes.

Cancel anytime