Top up balance
Minimum deposit: $5.00
Send via PayPal to:
—
⚠️ Deposited balance is non-refundable for any reason.
AI creative tools
⚠️ Log in or sign up to generate.
Minimum deposit: $5.00
Send via PayPal to:
—
Send crypto (—) to:
—
🇮🇩 Pay with DANA to:
0859-6023-4426
$5.00 ≈ Rp 90.000
Open DANA app
Scan the QR from another phone, or tap the button on this phone. Enter the rupiah amount shown above.
⚠️ Deposited balance is non-refundable for any reason.
Tap the account icon at the top, then sign up with an email and password. Once logged in, your session is used automatically across every tool — no need to log in again when you switch pages.
On the login screen tap “Forgot password?” (or the green WhatsApp button) and send the email you signed up with. The admin resets it and sends you a new password, usually within a few hours. Your balance, history and free uses stay the same — just log in with the new password.
Free Tools are file converters you can use as much as you like with a free account (just log in — no top up needed): Image Converter (JPG, PNG, WEBP, and iPhone HEIC to JPG), Image Compressor, Image Resizer, Images to PDF, PDF to Images, Video to MP3, Video to GIF, Blur / Mosaic, Move Image Part and Audio Converter. They run entirely on your own device — your files are never uploaded.
Tap the "Balance · Top up" button in the header. Choose a payment method (PayPal or Crypto), send the payment as instructed, then send your proof of payment via WhatsApp. An admin reviews it and your balance is added once approved — usually within a few minutes to a few hours.
Top ups need to be manually reviewed by an admin (it's not instant). Make sure you've sent proof of payment via WhatsApp. If it's been several hours, contact us via the WhatsApp button in the bottom-right corner.
No. All balance top ups and feature usage are final and non-refundable for any reason, including any unused balance. Please double-check the amount and payment method before you send payment.
Balance charged for a generation cannot be refunded, since the underlying AI cost is incurred as soon as the job runs — even if the result isn't what you wanted. Make sure your description/prompt is clear before hitting Generate.
Every tool shows an "Estimated cost" before you click Generate — this number matches exactly what's charged to your balance, no hidden fees. If your balance is too low, the Generate button will show an insufficient-balance message.
Every tool page has a "History" section below the result — your generations are saved automatically in your browser (not on our servers), so switching devices or clearing browser data will lose it. Download anything important.
Upload a video (up to 30 seconds) and the AI finds and removes platform watermarks like TikTok or CapCut on its own — no painting needed. You'll see the estimated cost before you start; it's billed per second of video.
For censoring part of a photo or video — paint over the area you want blurred; it's processed instantly in your own browser (not through the server), so it's fast and free.
Auto Captions transcribes the speech in your video and generates a downloadable .srt subtitle file, ready to attach to your video.
It translates the speech in a video into another language while keeping the original speaker's voice style — not a generic robotic voice.
It chains multiple scenes/clips into one continuous video — handy for building a short story out of several AI-generated clips.
Write as detailed a description as you can (colors, style, lighting, composition). The more specific the prompt, the closer the result matches what you had in mind.
It lifts a piece of a photo and moves it to a different spot in the same photo. The gap it leaves behind is filled with white, black or left transparent. It's free and works on your device.
Background Removal cuts the subject out from its background (making it transparent). AI Enhance upscales and sharpens a blurry or low-resolution photo or video.
Yes — it smooths skin and enhances facial detail naturally, it doesn't drastically reshape faces or bodies.
Aimed at game developers — Sprite Sheet produces ready-to-use animated characters, Game Assets produces backgrounds, tiles, props, and UI elements.
Text to Video creates a video clip from a written description. Image to Video animates a photo you upload into a moving video (optionally with audio).
It generates ready-to-use 2D visual effects for games, like explosions, sparks, or attack effects.
Music Generator freely creates instrumental tracks or songs with lyrics. Song Generator is more structured — you can set up verse/chorus sections yourself.
Voice Changer converts a recording of your own voice into a different voice. Text-to-Speech turns written text into spoken audio (30+ languages supported).
It generates short sound effects (footsteps, explosions, nature sounds, etc.) from a text description — useful for videos or games.
Yes — open the drawer menu (☰) in the top-left corner and pick a language from the list at the top of the menu. Translation is automatic and free, and it's remembered on your device so the next visit is instant.
Try generating again — sometimes the AI server is busy. If it keeps failing, contact us via the green WhatsApp button in the bottom-right corner and include a screenshot of the error.
Tap the green WhatsApp button in the bottom-right corner to chat directly with an admin.
No results. Try a different keyword, or ask directly via the WhatsApp button below.
AI video cleanup
Made for cleaning up your own footage. Upload a video and a dedicated AI watermark-removal model does detection and inpainting in one pass. Works best on clips up to 30 seconds — longer videos take much longer to process and are more likely to time out, so there's a hard limit here to keep rendering fast.
The dedicated watermark-removal model finds and removes the watermark on its own — no input needed from you. Works best on standard platform watermarks (TikTok, CapCut, etc).
Paint over the watermark on the video above — the same area is cleaned across the whole clip. Use this when the automatic detector misses it, or to target one specific logo precisely.
Zoom in and switch to "Pan" to scroll around, then back to "Draw" to paint precisely over small watermarks.
Drag this to find the exact moment the watermark is clearest, then paint over it — your painted marks stay even if you scrub to a different frame.
Uses a dedicated, temporal-aware watermark-removal model built specifically for this, not a general chat model.
Upload a video and get back a written description you can reuse as a prompt — for video-generation tools, captions, or cataloguing. Works best on clips up to 15 seconds; longer videos are much more likely to fail or time out during analysis. Uses the same account as Watermark Remover.
Runs a separate speech-to-text pass (OpenAI Whisper) alongside the visual analysis and merges the transcript into the result.
After the free uses (or if the free AI is busy) it uses your balance · ~$0.06 per video + ~$0.06 for dialogue transcript
Uses a dedicated video-understanding model to analyze what's happening in the clip and write it out as text.
Create unique effect assets for your 2D game, including animations and visual effects. Generates a short isolated VFX clip you can key out or composite into your game — powered by a text-to-video model.
Generate game-ready animated sprite sheets from text descriptions, or switch to 3D mode to turn a character into a riggable 3D model. Pick the animations you need, describe your character (or upload a reference), and get back an asset ready to use in your game engine.
Outputs a 3D model file (GLB) instead of a flat sprite sheet — a reference image gives much better results than text alone, since the model builds the 3D shape from what it sees.
More frames = smoother-looking animation, but each individual frame gets smaller (the image can only be so wide) — past ~16 frames, detail starts to drop noticeably. If you just want smoother-*looking* playback without losing quality, try lowering the Speed slider in the preview instead.
Keeps Walk/Run/etc. consistent — every frame faces the same way instead of flipping around.
Adds a skeleton so the model can be animated in Unity, Unreal, Blender, etc. Works best on a single humanoid character with clearly separated arms/legs.
From Meshy's library of 500+ presets — the ones above are common examples. Look up more IDs at docs.meshy.ai if you need something specific.
Generate sound effects with AI. Create unique sounds for any purpose — UI clicks, impacts, ambience, whoosh, footsteps, and more.
Create original music with AI, including full songs with lyrics or instrumental tracks. Powered by ACE-Step 1.5 (up to 4 minutes, 50+ languages).
Generate original songs with lyrics using AI technology. Powered by MiniMax Music v1.5 — write structured lyrics with [verse] / [chorus] / [bridge] tags for best results.
At least 10 characters — a single word like "Pop" isn't enough for MiniMax to work with.
MiniMax Music v1.5 has no direct duration control — the song's length comes from how much lyrics/sections you write. This just fills in a structure template to match; edit the words freely.
Use section tags like [intro], [verse], [chorus], [bridge]. Keep it under ~600 characters for cleanest results.
Upload any image and get a detailed AI-art prompt that describes it — useful for recreating or remixing a style with Text to Image.
After the free uses (or if the free AI is busy) it uses your balance (~$0.03).
Generate a background image from a text description — for thumbnails, product shots, streams, or design work.
Upload a reference photo of a character and describe a new pose, scene, or outfit — keeps the same character consistent across images.
Repair scratches, fading, noise, and other damage in an old or vintage photo.
Transform a photo into Studio Ghibli-inspired anime art.
Convert photos between JPG, PNG and WEBP — including iPhone HEIC photos to JPG. Add several at once.
Make photos much smaller (great for WhatsApp, websites and uploads) while keeping them looking good.
Resize photos to an exact size — or pick a ready-made size for TikTok, Instagram or YouTube.
Leave one box empty to keep the original proportions.
Turn photos or screenshots into one PDF document — perfect for receipts, documents and notes.
Use ↑ ↓ to change the page order.
Turn every page of a PDF into a JPG or PNG image.
Take the sound out of a video and save it as an MP3 — music, voice-overs, podcasts.
Paste a TikTok link and save the video without the watermark — in HD when available — or just its sound as MP3, or the photos of a photo post. Please only download videos you made or have permission to use.
In TikTok tap Share → Copy link, then paste it here.
iPhone: after the download finishes, open the Files app (Downloads) → share → Save Video to put it in Photos.
A full video editor that runs completely in your browser — cut, trim and join clips, transitions, filters and colour, text with animations, subtitles, stickers and overlays, music, sound effects and voice-over, templates, then export as video, GIF or photo. 100% free, nothing is uploaded, your project saves itself on this device.
Drag text and stickers on the preview to move them; pinch (or use the Size slider) to resize.
Tap an item to select it. Drag a selected clip to reorder it, drag its white edges to trim. Drag selected text, stickers and sounds to move them in time. Pinch or use the slider to zoom.
Type what is said, one line per subtitle. Each line is placed one after another from the playhead.
Add your clips first, then tap a template — it sets the size, transitions, filters and ready-made text you can edit.
Your project saves automatically on this device.
Saves the frame at the playhead as a full-quality photo.
Video export plays your project once while recording it, so it takes about as long as the video. Keep this page open and on screen until it's done.
Make a GIF from any part of a video — for memes, stickers and reactions.
Tip: pause the video above where you want the GIF to begin and tap “Use current time”.
Convert audio files (M4A, WAV, MP3, AAC, OGG…) to MP3 or WAV.
Upload a long video and let AI find the best moments to cut into short clips — get exact timestamps, a hook/caption idea, and why each moment works. (This finds the highlights and gives you timestamps; it doesn't cut the video file itself — use the timestamps in your editor, or feed a clip's time range into Text to Video/Video to Prompt for repurposing.)
After the free uses (or if the free AI is busy) it uses your balance · ~$0.09 per video
Restyle an existing video with a text prompt — turn footage into anime, painting, cinematic looks, or make targeted edits, powered by Luma.
Upload a portrait photo and type what they should say — get a realistic talking video with lip-sync, no filming or voiceover recording needed.
Turn a single photo and an audio track into a long-form talking or singing avatar video — up to 10 minutes, with natural expressions and full-body lip sync.
Locked to 480p for now to keep cost predictable — 720p costs roughly 2× more per second on the underlying model and isn't priced separately yet.
Sync a video's lip movements to a different audio track — great for dubbing into another language or replacing a voiceover, powered by Veed.
Tip: you can generate the new voice track first with AI Text-to-Speech or Voice Changer, then upload it here.
Generate backgrounds, tilesets, props, and UI elements for your 2D game. Describe what you need (or upload a reference), pick an asset type and art style, and get back an image ready to drop into your game.
Recommended for props, items, and UI elements you'll place over other art.
Useful for backgrounds and tilesets meant to repeat edge-to-edge without visible seams.
Turn a reference photo into a textured 3D model (GLB) — with optional auto-rigging and animation for game-ready humanoid characters, powered by Meshy V7.
Best results: a centered subject, clear background, one clear character or object.
~40 curated presets above. Full list of 697: docs.meshy.ai/en/api/animation-library — pick "Custom animation ID" and type any ID from there.
Turn a background, stage, or environment photo into a 3D scene (GLB) — use it as a real 3D backdrop behind a dancing/animated character, in a game, or in a 3D viewer. Powered by Meshy V7 (same model as 3D Character Generator, without rigging).
Best results: a wide shot of the stage/room/environment, even lighting, minimal foreground clutter.
New: works on photos too — tap 🖼️ Photo below.
Paint over any area — a face, a license plate, a screen, anything — and it gets blurred or pixelated across the whole clip. Free and instant — everything happens on your device, nothing is uploaded. Works on clips up to 20 seconds.
Paint over the faces, plates, text or anything you want to hide — the effect shows right away.
The censored area stays fixed to where you paint it — if the subject moves a lot across the clip, paint a slightly larger area to cover its range of motion, or switch to "Track a moving subject" above.
Drag this to see the exact moment the subject is where you expect, then paint over it — your painted area stays even if you scrub to a different frame.
A tracking model follows this subject frame by frame, so the censored area moves with it across the whole clip's tracking mode.
Needs enough balance and takes longer than the free fixed-spot mode, since it uploads the video and runs a tracking model first.
Generate an image straight from a text description — no reference needed.
You can write this in any language — it's auto-translated to English before generating, since the image model follows English descriptions far more accurately.
Paint over a part of a photo — an eye, a logo, an object — lift it out, then drag it anywhere else on the image. Great for meme-style edits or quick composites. Images are processed at up to 1024px wide for performance.
Drag the lifted piece anywhere on the image. Use the slider to resize it.
Generate a short video clip straight from a text description.
You can write this in any language — it's auto-translated to English before generating, since the video model follows English descriptions far more accurately.
⚠️ This model officially only documents 16:9 and 9:16. A custom size may be rejected by the API or produce distorted results — use multiples of 16, and test with a cheap short clip first.
Animate a still photo into a video clip with native audio, using MiniMax H3 — describe the motion you want, optionally set an end-frame image, and get a short animated clip up to 15 seconds. The output video automatically matches your source photo's aspect ratio — upload a portrait photo for a 9:16 video, a landscape photo for 16:9, and so on.
Write out your video as a series of scenes, and each one is generated to continue exactly where the last one left off — the last frame of each clip becomes the first frame of the next, then everything is stitched into one continuous video. Up to 15 seconds per scene, up to 6 scenes.
Leave this empty and scene 1 will be generated from its own description instead (text-to-image first, then animated).
Each scene is billed separately (it's a full generation), plus a small fee for stitching the final video together. Total cost scales with how many scenes you add.
Upload a video and get a downloadable subtitle (.srt) file, generated automatically from the speech in it.
After the free uses (or if the free AI is busy) it uses your balance · ~$0.06 per video
Translate a video's spoken audio into another language while keeping the original speaker's voice characteristics and timing — powered by ElevenLabs Dubbing.
Convert a voice recording into a different voice character while keeping the original timing, emotion, and delivery — powered by ElevenLabs.
Smooth skin and enhance facial detail in a photo. Note: this retouches a still image — it does not do live/real-time face tracking, which is a different kind of technology (on-device AR, not a single API call).
Lower = subtler, more natural. Higher = more smoothing/enhancement.
Automatically remove the background from a photo or video, leaving a clean transparent cutout.
Upscale and sharpen a blurry or low-resolution image or video.
Turn written text into natural-sounding speech — supports 30+ languages, with automatic accent adaptation. Powered by ElevenLabs Eleven V3.
0 characters
Lower = more expressive/varied. Higher = more consistent/monotone.
Free assistant. Some answers use Google Gemini — don't share personal info.
