Make any script speak in your own voice

Record a short sample once, then type anything you want said.

Clone my voice

Cancel anytime · No watermark on any plan

Make any script speak in your own voice

Record a short sample once, then type anything you want said.

Cancel anytime · No watermark on any plan

Make a Photo Talk With Your Own Voice Recording (Nov 2026)

Percify Team

Percify Team

Content Writer

November 19, 2026
6 min read

Made with Percify

Talking videos of you, from one photo

Quick Answer

Record what you want to say, then give a lip sync tool two files: the photo and your recording. It renders a video in which the face in the photo speaks with your real voice, and the video is exactly as long as the recording.

Record your voice, pick one photo, and a lip sync tool renders the photo speaking your recording. How to record it well, the steps on Percify, and how HeyGen, Hedra, D-ID and two open models handle the same job, checked 19 November 2026.

Cover for the guide to making a photo talk with your own voice recording

Record what you want to say, then give a lip sync tool two files: the photo and your recording. It renders a video in which the face in the photo speaks with your real voice, and the video is exactly as long as the recording.

This is different from typing a script and letting an AI voice read it. Here nothing is synthesised on the audio side: it is your recording, with your timing and your tone, and only the picture is generated. Every limit and price below was read on the maker's own page on 19 November 2026. Percify is a paid product: making videos needs a plan.

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

Make this with your photo

Step 1: record your voice so the lips can follow it

The model reads the sound to decide how the mouth moves. A clean recording gives cleaner lips.

  • Use the voice recorder on your phone, held about a hand's width from your mouth, in a quiet room with soft furniture. Bathrooms and empty rooms echo.
  • Speech only. No music under your voice and no second speaker. Whatever is in the file ends up in the video.
  • Start and stop cleanly. Leave half a second of silence at each end and trim longer gaps. The video is as long as the file and the model bills per second of audio, so silence costs the same as speech.
  • Keep the first one short. Record 5 to 10 seconds for a test before you record the full message.
  • Save it as a common audio file. We used an MP3 for the example on this page.

Step 2: choose the photo

  • One clear face, looking at the camera, in good light.
  • Mouth closed or nearly closed, with nothing in front of the lips: no hand, microphone, cup or mask.
  • Whose face is it? Use your own photo, or a photo of someone who has clearly agreed to it. Percify's terms do not allow making a talking video of a person without their explicit consent, or impersonating anyone.

Step 3: put the two together on Percify

  1. Open InfiniteTalk Fast ↗. The form is visible before you sign in. Making videos needs a plan.
  2. Add the photo in the Image field.
  3. Add your recording in the Audio field.
  4. Run the model. It bills per second of your audio, so trim the recording first.
  5. Download the MP4.

What it costs. On 19 November 2026 the pricing page showed four plans: Starter at $12 a month, Creator at $26 a month, Scale at $65 a month and Ultra at $128 a month. The same page puts a 15 second talking video at about 30 credits, and Creator at 1,233 credits a month. No plan puts a watermark (except Remake replicas, which carry a small AI-disclosure mark) on the video.

Worked example: one photo, one audio file, one clip

This is a real run on Percify. The person in the photo is AI generated and the audio is a generated voice line saved as an MP3, so no real person appears on this page. The steps are the same when the MP3 is your own recording.

The still photo used as the image input

The photo that went into the Image field.

The clip InfiniteTalk Fast returned for a 5 second audio file.

Other tools that take a photo and your recording

ToolYou give itWhat we read on its pages on 19 Nov 2026
PercifyA photo and an audio fileInfiniteTalk Fast is billed per second of audio. No watermark on the video on any plan. Paid from Starter $12 a month.
HeyGen ↗A photo avatar made from your photo, then a script or an uploaded audio fileFree plan: 3 videos a month, watermarked, up to 1 minute each, up to 3 photo avatars. Presenter Mode runs up to 30 minutes. Paid from Creator $29 a month.
Hedra ↗A start frame image and an audio file (Character 3)Up to 10 minutes, 540p, 720p or 1080p. Its plans page lists no free plan. Paid from Basic $20 a month.
D-ID ↗A face image (JPEG or PNG, up to 10 MB)Its studio page lists audio as an input. We did not find wording about uploading your own recording, so check that in its trial before you pay. See its pricing page.
SadTalker ↗ (open model)One portrait image and audioApache 2.0 licence. You install and run it on your own computer. No plan, your own hardware.
InfiniteTalk ↗ (open model)An image and audioApache 2.0 licence. Its authors warn that colours drift in image to video beyond 1 minute. No plan, your own hardware.

HeyGen asks for one extra step. You first turn the photo into a photo avatar in its Avatars section, then in the Single Scene tool's Presenter Mode you "write your script or upload an audio file". Its pricing table has an "Audio input" row. We could not read which plans it applies to, so check that row before you subscribe.

Hedra's Character 3 takes the image as a start frame together with the audio track, like Percify does.

D-ID is the one we could not confirm for this job. Its pages describe typed scripts and AI voices, and we found no wording about uploading your own recording.

The two open models do the same job on your own computer with no plan and no watermark. You install them and run them yourself.

Your recording or a typed script: which is better?

  • Use your own recording when the voice matters: a message to family, a greeting, a course intro in your own tone, anything where people should hear that it is really you.
  • Type a script instead when you want to change the words often or you do not like recording yourself. Then a voice model reads the text and the same lip sync step follows. On Percify that is two runs: a voice model such as ElevenLabs V4 Turbo ↗ first, then InfiniteTalk Fast.

What this does not do

  • It does not fix a poor recording. InfiniteTalk Fast does not remove noise, music or echo. Clean the audio before you upload it.
  • It does not change your voice. The audio in the video is the file you gave it.
  • It does not film anyone. The video is generated from one still photo. It is not a recording of the person.
  • It does not move a waveform or a logo. If you only want a still picture with your audio under it, our audio to video converter does that simpler job in the browser.

Test with a 5 to 10 second recording first. You see how the lips follow your voice on that photo before you spend on the full message.

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

Record what you want to say, then give a lip sync tool two files: the photo and your recording. It renders a video in which the face in the photo speaks with your real voice, and the video is exactly as long as the recording.

Yes. Here nothing is synthesised on the audio side: it is your recording, with your timing and your tone, and only the picture is generated. The audio in the video is the file you gave it.

Use the voice recorder on your phone, held about a hand's width from your mouth, in a quiet room with soft furniture. Record speech only, with no music under your voice and no second speaker. Record 5 to 10 seconds for a test before you record the full message.

Use your own photo, or a photo of someone who has clearly agreed to it. Percify's terms do not allow making a talking video of a person without their explicit consent, or impersonating anyone.

Use your own recording when the voice matters: a message to family, a greeting, a course intro in your own tone. Type a script instead when you want to change the words often or you do not like recording yourself. Then a voice model reads the text and the same lip sync step follows.

talking photolip syncvoice recordingcomparison
Percify Team
Published on
Share article

Related Reads

Make an Old Family Photo Speak a Message (Nov 2026) - Percify AI Avatar Blog Cover
Make An Old Family Photo SpeakNov 19, 26

Make an Old Family Photo Speak a Message (Nov 2026)

Scan the old photo, record or type the message, and a lip sync tool renders the face speaking it. Only for your own old photo or a living relative who agrees. Steps on Percify and how HeyGen, Hedra, D-ID and two open models compare, checked 19 November 2026.

Read Article
Audio File + Photo of Yourself to a Talking Video (Nov 2026) - Percify AI Avatar Blog Cover
Audio File And Photo To Talking VideoNov 19, 26

Audio File + Photo of Yourself to a Talking Video (Nov 2026)

Give a lip sync tool your photo and your audio file and it renders a video of you speaking the recording. Percify, HeyGen, Hedra, D-ID and two open models compared on their own pages on 19 November 2026.

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
Best AI UGC Ad Generators in 2026, Compared - Percify AI Avatar Blog Cover
Best AI UGC Ad GeneratorSep 12, 26

Best AI UGC Ad Generators in 2026, Compared

Creatify, Arcads, MakeUGC, HeyGen, AdCreative.ai and Percify: what each one makes, what it costs to start, and the limit you hit first. Checked 12 September 2026.

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
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

Make your first talking video

One photo and a script is all it takes.

Cancel anytime