Talking avatar from one photo
One front-facing photo and a short script. The mouth follows the voice, and the clip lasts as long as the speech.

Upload a photo and type what it should say. The Renoise Agent gives it a voice and makes your avatar talk.
Opens in the Renoise Agent with your photo and request.

Real model output from one photo and a typed script.
One front-facing photo and a short script. The mouth follows the voice, and the clip lasts as long as the speech.

A phone-selfie style review with product close-ups and stickers added in the same Agent project.
Sum up a book, a lesson or a question. The presenter talks while cards and pictures appear beside her.
The same presenter greets viewers in French, Spanish, Japanese and Chinese, each line written for that language.
Use your recording as is, or clone your voice from a clean 15-second clip.
No recording? The avatar speaks your script itself, or Gemini 3.8 Flash TTS reads it in one of 30 voices.
Takes of up to 30 seconds are checked and joined into one video.
Add product shots and B-roll from other video models in the same Agent project.
Upload one clear, front-facing photo and add a script or a recording of speech. The Renoise Agent cuts the script into short takes and Wan 3.0 makes your photo say each one, with natural gestures and expressions; with a recording, each take lip-syncs to a piece of it of up to 15 seconds. The takes are checked and joined into one video of any length, at 720p by default and up to 1080p.
The clip at the top of this page was made before Wan 3.0 became the default, with OmniHuman 2.0: one photo, a 30-word script, about 10 seconds of video. You can still ask the Agent for OmniHuman by name.
The request opens in the Renoise Agent. See how the Renoise Agent works.
One front-facing or three-quarter photo with the face and mouth clear. Every take is made from it, so the face stays the same.
Type a script, or add a recording of your own speech in the Agent chat.
The Agent makes Wan 3.0 takes of up to 30 seconds and joins them. At 720p that is 12 credits per second of video.
Real avatar films from Renoise Avatar Studio. Open one there to make your own version with your topic, photo or voice.
HeyGen is the larger avatar platform: more ready-made presenters, longer videos, translation. Renoise is the choice when the avatar is your own photo and voice and the video also needs generated shots.
| Feature | HeyGen | |
|---|---|---|
| Ready-made presenters | 18 in Avatar Studio | 700+ on Creator |
| Start from your photo | ✓ One authorized portrait | ✓ Photo avatars |
| Video length | Any length, joined from takes of up to 30 s | 30 minutes on Creator |
| Output resolution | 720p, up to 1080p | 1080p on Creator, 4K on Pro |
| Video translation | ✓ 29 languages, lips not re-timed | ✓ 175+ languages |
| Generated product shots | ✓ Seedance 2.5, Kling 4.0 and more, from Starter | Seedance 2.5 on Pro |
Renoise: models API and Avatar Studio, checked 2026-11-06; Wan 3.0 route and dubbing 2026-11-19. HeyGen: heygen.com/pricing and help.heygen.com articles 15126059 and 17680953, accessed 2026-10-27.
A photo avatar is your portrait turned into a presenter. The Agent writes or takes your script, cuts it into takes of one or two sentences, and Wan 3.0 performs each one from your photo, speaking the line with gestures and expressions; each take runs up to 30 seconds, and the takes are checked against the script and joined, so the video can be as long as you need. Output is 720p by default, with 1080p on request.
To use a voice you already have, such as your own recording, a voiceover in your cloned voice or a song, the Agent cuts the track at pauses into pieces of up to 15 seconds and each take lip-syncs to one, so the finished video plays that exact audio. A script can also be read first by Gemini 3.8 Flash TTS in one of 30 voices, or in your cloned voice. Wan 3.0 costs 12 credits per second at 720p, so 10 seconds is 120 credits, and 6 per second at 480p. OmniHuman 2.0, which made the example at the top, is still available if you ask for it by name.
A photo avatar talks to the camera. It does not pick up a product, walk through a room or change scenes. Those shots come from generative video models such as Seedance 2.5 or Kling 4.0, and the Agent can cut them together with the talking parts, which is how the Avatar Studio films above were made. The AI video generator page lists those models.
Two neighbouring jobs have their own pages: making a person in an existing video say new lines is AI lip sync, and bringing an old photo to life with a short line is an AI talking photo.
Only use faces and voices you have the rights to: your own, or someone who has authorized it. Public figures and minors are not allowed.
What happens to an uploaded photo or voice recording, in plain words.
Picking a file only previews it on your device. Not one byte is stored until you sign in and click generate.
Uploads land in your private library, never a public gallery, and re-running the same photo or voice recording stores nothing new.
Remove uploads and results from your library whenever you want.
As of October 2026, 100,000+ creators in 170+ countries and regions use Renoise AI, an AI video, image and audio platform, to generate 300,000+ images and videos with 30+ models.
Source: Renoise internal data, March–October 2026. Figures are rounded down and updated quarterly. Last updated
Real feedback from creators who use Renoise AI to make videos, images and ads.
Renoise is pretty easy to use, with a clean and smooth interface. The results from Seedance 2.5 also feel noticeably smoother in action sequences.
Renoise Ai is a good tool for making ai videos and photos. it puts several Ai models in one place, so you don't need to use many different apps.
あまりAIツールを使ったりしたことなかったですが、キャラクターの固定や動画を続いて作成できて使いやすいです。これからどんどん進んでいくアップデートが楽しみです。
Renoise has been a great platform for AI creativity. The tools are easy to use, the experience is smooth, and it makes creating content more enjoyable and efficient. I really appreciate the work the team is doing and look forward to seeing more improvements. Highly recommended!
What I like about Renoise AI compared to other platforms: Fast generation speed: Slow generation takes up way too much time, but Renoise AI is surprisingly about 30% faster. Intuitive and user-friendly UI: Cheaply made platforms have terrible UIs that make me not even want to log in, but Renoise is very clean and convenient. Remembers my previous settings: It helpfully remembers my last workspace settings. Some odd platforms force you to re-adjust everything every single time you generate a video, which is extremely frustrating. Overall preference: For all these reasons, Renoise AI is definitely my preferred platform. Thank you!
Renoise is your go to one stop all for ai creators. all view and use all models in one place, for any type of content you have your mind on!
I have a creat experience with the app. Consistent characters but also unique. THere were some issues with storyline continuity and non-typical humanoid characters.
One plan unlocks every video model, plus the image and audio models.
For your first AI creations
per month
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For your first AI creations
per month, billed annually
Save $48compared to monthly
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month, billed annually
Save $216compared to monthly
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month, billed annually
Save $960compared to monthly
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
Not here: there is no free plan. Wan 3.0 avatar takes cost 12 credits per second at 720p, so a 10-second clip is 120 credits, or 60 at 480p. The 20 credits for following us on X and YouTube do not cover one clip.
Yes. Upload your own photo and add your own recording, or clone your voice from a clean 12–20 second clip of you reading aloud. Only your own face and voice, or those of someone who has authorized it.
There is no fixed limit. Each take runs up to 30 seconds, and the Agent joins the takes in order into one video, so a two-minute video is simply more takes.
One person, facing the camera or turned slightly, with the mouth clear of hands, hair or a microphone and even light on the face. Every take is made from this one photo, so a clear, well-lit face matters more than the crop; say in the chat if the video should be vertical or wide.
Yes. The box on this page takes images, so add the recording in the Agent chat after you start, or begin in Avatar Studio, which takes a photo and a voice clip together. The Agent cuts it at pauses into pieces of up to 15 seconds and each take lip-syncs to one, so the video plays your own voice. It needs speech or singing, not music alone.
Yes. Write the script in that language or ask for one; the voice reads it and the lips follow. To translate a video you already made, the Agent can dub it into 29 languages with ElevenLabs Dubbing, keeping the picture and background sound; the lips are not re-timed, so for an avatar facing the camera, making it again in the new language looks better.
It depends on the job. For a large library of ready-made presenters, translation and long training videos, HeyGen or Synthesia fit better. For your own face and voice plus generated product shots in one project, from the browser or Claude Code, Renoise fits.
Yes. The clay bear and the Shiba Inu presenter above were made in Renoise Avatar Studio. For non-human characters the Agent generates the talking shots with a video model instead of driving a photo.
This page makes talking videos. For a still avatar or profile picture from your selfie, see the AI profile picture guide.
No. Use only faces and voices you have the rights to. Avatars of public figures, of minors, or of anyone who has not agreed are not allowed.
Upload a portrait, add a script or a recording, and pick a presenter style.