AI Digital Human

Upload a portrait image, then either upload an audio file or record one with your microphone. The image is checked first, and the lip-synced video is generated only when it passes. Choose 480P or 720P; audio must be 20 seconds or shorter. Combined billing: an image check ¥0.5 per run plus 480P ¥1 per second or 720P ¥2 per second. If the image is rejected or generation fails, only the check fee is kept and the generation fee is refunded. Videos are deleted after 24 hours.

Pay per use, no sign-up, Alipay and WeChat Pay; only after payment succeeds are the portrait image and voice audio sent to our backend as URLs. The image is checked first, and the video is generated only when the check passes. The generated video file is deleted after 24 hours.

More tools in Image tools

Frequently asked questions about AI Digital Human

How much does this tool cost?
Combined billing: an image check costs ¥0.5 per run and is charged whenever the check call succeeds, plus a generation fee based on the audio length rounded up to whole seconds — 480P ¥1 per second or 720P ¥2 per second. The page shows the total before you pay, and one payment covers one generation.
What if my image is rejected or generation fails?
A rejected image never starts video generation and the page says clearly that a digital human cannot be generated. A successful check call incurs the ¥0.5 check fee; the per-second generation fee is refunded automatically. A failed or timed-out generation task is charged the check fee only, and if the check itself cannot complete the whole payment is refunded.
Are there limits on the audio?
You can upload a WAV or MP3 file, or click "Start recording" to capture audio with your microphone. Either way the file must be under 10 MB and the audio no longer than 20 seconds (the video has the same length as the audio). Recording stops automatically at 20 seconds; longer clips are blocked with the message "Each digital human video must be 20 seconds or shorter". The server checks the duration again when the order is placed and before each generation.
Can I record audio with my microphone?
Yes. Click "Start recording" and allow microphone access. Recording stops automatically at 20 seconds, and you can stop it manually at any time. The clip is converted to WAV in your browser before uploading and is billed exactly like an uploaded audio file. If your browser does not support recording or you deny microphone access, just upload a WAV or MP3 file instead.
How long is the generated video kept?
The video URL returned by the generation service is valid for only 24 hours, so we download the video to our server first and give you a local link to play and download. The file is deleted from disk after 24 hours — please save it in time.
How are my image and audio handled?
Both files are uploaded to our site first and exchanged for accessible URLs that are submitted for generation; the browser and backend exchange URLs only. Uploaded files and the resulting video are kept for 24 hours. The image is always checked first, and video generation starts only when the check passes.
Will processing overwrite the original file?
No. The original stays read-only and the result is saved as a new download you can review before replacing anything; the original file is never touched.
Which image formats are supported?
Input accepts any common format the browser can decode (JPEG, PNG, WebP, GIF, BMP and more); export supports JPEG, WebP and PNG, and each tool offers whichever of those its page lists (code-to-image exports PNG or JPEG, image-to-ASCII exports TXT / PNG / SVG / HTML).
Are images uploaded to a server?
Not for anything except AI watermark removal, AI background removal, AI image generation, AI upscaling and AI ID photos. Compression, cropping, rotation, collage, image-to-Base64, code-to-image and image-to-ASCII all run locally in the browser, so images never leave your device; the five AI tools need model inference, so the content (the image or the description) is submitted to our backend only after payment succeeds, and the result image is sent straight back to the browser. The source image used by AI image generation and AI upscaling is also uploaded to our site, only so the model can fetch it; AI ID photos send the source image with the processing request instead and keep nothing on our side. No AI page ever shows or hands out an image link, and result images are never written to disk.

About Local Toolbox

Local Toolbox groups the small tools you reach for every day by what you are doing: formatters and converters, date maths, documents and résumés, codes and ID cards, images, encryption, diagramming, and annotation and accounting. Open a page and start working — no sign-up, and almost every tool has no usage limit.

Most features compute inside your browser, so your input never leaves your device; the pages are plain static assets, load fast and keep working offline. The IP page asks our backend for your outbound address when it opens and sends none of your input. AI watermark removal, AI background removal, AI image generation and AI upscaling send content to our backend for inference (watermark removal is ¥1 per run; background removal is ¥1 per run; image generation and upscaling are priced by resolution — 2K ¥2, 4K ¥3); AI annotation sends images to a large model that locates the target and returns coordinates (¥0.5 per image, refunded only when every image in the batch fails); AI flowchart, AI mind-map and AI Mermaid chart generation send your text description to a model that builds the diagram (three separate products, charged ¥0.5, ¥0.5 and ¥0.5 per run respectively); and the accounting helper sends the income, expense, social-insurance and balance figures you fill in to generate a report (¥0.5 for the spoken analysis, ¥1 for the report). These features accept Alipay and WeChat Pay, upload nothing before payment succeeds, and refund automatically if processing fails.

Links