Quick Answer
You need a tool that takes two files, one photo of your face and one audio file, and renders a video in which the face speaks the recording. That job is called audio driven lip sync or a talking photo: on Percify you add the photo and the audio to the InfiniteTalk Fast model and download an MP4, and HeyGen, Hedra and D-ID offer their own versions of the same job.
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.
Keep reading
Related next steps

You need a tool that takes two files, one photo of your face and one audio file, and renders a video in which the face speaks the recording. That job is called audio driven lip sync or a talking photo: on Percify you add the photo and the audio to the InfiniteTalk Fast model and download an MP4, and HeyGen, Hedra and D-ID offer their own versions of the same job.
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.
What you need before you start
- One photo of you. Face to the camera, good light, mouth closed or nearly closed, nothing covering the lips.
- One audio file. Your own recording, for example an MP3 (the format we used), speech only, as little background noise as you can manage. The video will be as long as the audio.
- The right to use both. Use your own face and your own voice, or have the clear permission of the person in the photo and the person speaking.
Tools that take your photo and your audio file, at a glance
| Tool | You give it | What we read on its pages on 19 Nov 2026 |
|---|---|---|
| Percify | A photo and an audio file | InfiniteTalk 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 file | Free 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 audio | Apache 2.0 licence. You install and run it on your own computer. No plan, your own hardware. |
| InfiniteTalk ↗ (open model) | An image and audio | Apache 2.0 licence. Its authors warn that colours drift in image to video beyond 1 minute. No plan, your own hardware. |
How to do it on Percify
- Open InfiniteTalk Fast ↗. The form is visible before you sign in. Making videos needs a plan.
- Add your photo in the Image field.
- Add your recording in the Audio field.
- Run the model. It bills per second of your audio, so a short recording costs less than a long one.
- 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.
What you get. An MP4 with your audio in it, with no watermark. InfiniteTalk's authors say the model moves the head, posture and expression with the audio, not only the lips.
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 here. The steps are the same with your own photo and your own recording.

The photo that went into the Image field.
The clip InfiniteTalk Fast returned for a 5 second audio file.
The other tools, one by one
HeyGen. You first turn your photo into a photo avatar in the Avatars section. HeyGen's help centre warns that a photo uploaded to Assets and dropped on the canvas will not be lip synced. In the Single Scene tool's Presenter Mode you then "write your script or upload an audio file". The pricing page lists a free plan with 3 watermarked videos a month of up to 1 minute each, and paid plans from Creator at $29 a month. 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. Character 3 needs a start frame and an audio track, and its model page lists a maximum of 10 minutes at 540p, 720p or 1080p. The plans page starts at Basic, $20 a month with 2,000 credits, and lists commercial use on every paid plan. It lists no free plan.
D-ID. The studio lets you upload a face image and names audio among its inputs. Its pages talk mostly about typed scripts and AI voices. We could not confirm on 19 November 2026 that you can upload your own recording, and its pricing page did not show us prices, so we state none here. Its own pages say trial videos carry a full screen watermark.
SadTalker and InfiniteTalk on your own computer. Both are open models under the Apache 2.0 licence that take one image and one audio file. There is no plan and no watermark. You pay with setup time and hardware: you install them, download the model files and run them yourself.
What these tools do not do
- InfiniteTalk Fast does not clean your audio. Noise, music and long silences in the recording go into the video as they are. Edit the audio first.
- Percify does not film you. The result is a generated video made from one still photo. It will look like you, and it is not a recording of you.
- None of the tools here turn a waveform or a cover image into a talking face. If you only want a picture with your audio under it, with no moving lips, that is a different and much simpler job. Our audio to video converter does that one in the browser.
- A group photo is a harder case. Use a photo with one clear face.
Which one to pick
- You have the two files and want the video now, without building an avatar first: Percify or Hedra, both take the photo and the audio directly.
- You want to reuse the same avatar of yourself in many scripted videos: HeyGen's photo avatar route is built for that.
- You have a graphics card and time, and you do not want a plan: SadTalker or InfiniteTalk.
Whichever you pick, test with a 5 to 10 second recording first. You see the quality on your own face before you spend on a long one.
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.
Cancel anytime from your profile
Got questions?
Frequently asked
You need a tool that takes two files, one photo of your face and one audio file, and renders a video in which the face speaks the recording. On Percify you add the photo and the audio to the InfiniteTalk Fast model and download an MP4. HeyGen, Hedra and D-ID offer their own versions of the same job.
One photo of you with your face to the camera, good light, mouth closed or nearly closed and nothing covering the lips. One audio file with speech only and as little background noise as you can manage. The video will be as long as the audio.
Percify is a paid product: making videos needs a plan. 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. InfiniteTalk Fast bills per second of your audio, so a short recording costs less than a long one.
SadTalker and InfiniteTalk are open models under the Apache 2.0 licence that take one image and one audio file. There is no plan and no watermark. You pay with setup time and hardware: you install them, download the model files and run them yourself.
On Percify you get an MP4 with your audio in it, with no watermark. The result is a generated video made from one still photo. It will look like you, and it is not a recording of you.
