Video Tools

Convert between mp4 / mkv / gif / webm / mov / ts with custom codec, resolution, bitrate, frame rate and audio settings.

Shrink video file size while keeping the format unchanged. Adjustable quality / bitrate / resolution with batch compression.

Extract audio from video or convert between audio formats. MP3 / M4A / AAC / WAV / FLAC / OGG and more (11 formats) with adjustable bitrate and sample rate.

Auto frame extraction + local LLM for streaming Q&A about the video

Draw boxes over video areas to hide license plates, faces, prices and other private info

Turn photo sequences into timelapse videos with fps, resolution, aspect fit and deflicker

Auto-extract highlights, condense still footage, speed up or manually cut clips, batch process long videos

Auto-split a full match recording into sound-based highlight clips with watermark naming for one-click sharing

Type a script, get a wave-animated talk video with local AI voice and per-sentence subtitles - no camera needed

AI video production with OpenMontage pipelines, stage checks, tool preflight, and local rendering.

Auto-transcribe speech and translate into bilingual subtitles; burn into video or export subtitle files

Type a script and local AI dubs the video, replacing or mixing the original audio - batch product explainers

Select the watermark area; local AI erases fixed or moving watermarks in fast or per-frame modes

Invisible watermark: unique subscriber ID, leaked videos traceable

One-click repurpose: random mix of mirror/speed/frame-drop/border/sticker/BGM, multiple variants with similarity self-check

Auto-segment podcasts/courses/live replays: audio highlights or ASR sentence scoring, vertical clips for distribution

Combine denoising, artifact removal, deflickering, stabilization, interpolation and color correction, with sample comparison and remuxing.

Deinterlace, denoise, stabilize, brighten and clean audio - digitize old tapes in high quality

Stabilize, deflicker, sharpen and convert to vertical in one pipeline

Merge dashcam segments in order, speed up, add BGM/timestamp; evidence mode exports every frame

Join multiple videos with music, speed and canvas controls using local FFmpeg with saved task history

本地保存混剪脚本和分镜素材

Combine product images and selling points into sales videos with local FFmpeg and persistent task history

Sample frames at intervals into a vertical long image with optional timecodes - for film explainers and recaps

Generate long gradient videos with noise or your own audio, fading out at the end - perfect for sleep

Sentence-by-sentence reading with silent repeat gaps and pinyin subtitles; parents create read-along materials in one click

Auto highlight from OBS footage by sound, cut segments with watermark and manifest, share to your fans

Adjust pitch and tempo of practice/covers independently, output MP3

Extract audio from video or convert between audio formats. MP3 / M4A / AAC / WAV / FLAC / OGG and more (11 formats) with adjustable bitrate and sample rate.

Transcribe audio / video locally (zh/en/yue/ja/ko) with timestamps and speaker labels; export SRT / TXT

6-stem vocal separation: split vocals/drums/bass/guitar/piano/other in one click, remix to export accompaniment or a brand-new mix

Type text and synthesize speech in one click: mixed Chinese/English, 103 voices, adjustable speed, all local and offline

Natural narration and voice cloning from reference recordings.

拖入 TXT 小说，自动识别章节、旁白和角色并生成有声书。

Transcribe audio in one click: polyphonic transcription (any instrument) to MIDI, with automatic numbered notation of the melody

Turn audio into podcast video: cover + waveform animation + progress bar, square/landscape/portrait for every platform

Precise metronome for practice: time signature, accents and subdivisions

Rain, waves, campfire and more ambient sounds for sleep, focus and relaxation

Pluck a string to see pitch and cent deviation, with 30+ instrument presets

Compare audio by content fingerprint to find identical or highly similar files

Upload a song; lyrics and timeline are auto-recognized, then edit and export LRC

Speech recognition + local LLM turns any podcast/recording into an article

Identify 6,522 bird species by sound (BirdNET), on-device AI

Deep denoise + de-click, make recordings clear in one click

Convert between audio formats (11 formats: MP3 / M4A / AAC / WAV / FLAC / OGG and more). Also supports extracting audio from video, with adjustable bitrate and sample rate.

Convert between 21 formats (JPG / PNG / WebP / GIF / BMP / TIFF and more) with custom resolution and aspect fit, batch supported.

Compress JPEG / PNG / WebP / TIFF / AVIF in their original format, with visually lossless and data lossless modes, batch supported

Compress JPG / PNG / WebP / AVIF / JPEG XL / GIF with adjustable quality (1–100); each format uses a dedicated professional compressor; batch supported

One-click subject cutout with precise hair and product edges, processed locally by AI without upload, with manual touch-up and batch support

Local Z-Image-Turbo text-to-image with Chinese text and batch generation

Erase visible watermarks with local AI inpainting and strip C2PA/EXIF provenance marks, with batch processing

Invisibly embed copyright info into images for provenance tracing

Generate QR codes from text / links / contacts with adjustable error correction, PNG / SVG, custom colors, center logo and batch generation

Batch-decode QR codes in images; auto-enhances blurry codes and auto-inverts dark backgrounds; copy or export results

Batch-combine images into PDF (page size / images per page / fit) and convert PDF pages to images (scale / format / page range)

Convert among ten common document formats — PDF, EPUB, Word, Excel, CSV, ODT, RTF, TXT, Markdown and HTML — all done locally

Vectorize images into SVG (palette / denoise / detail) and render SVG to bitmap (any scale / background)

Batch-add text / image watermarks with font, size, color, opacity, rotation, position and tiling; save named presets

Turn images into pixel art (block size / palette) and ASCII art (multiple charsets)

Add text bubbles and stickers to images to make your own memes

Snap a photo of a page; auto-correct perspective and enhance it into a clean scan

Merge, extract, rotate pages and add text watermarks while keeping originals.

Add hidden Chinese and English text layers to scanned PDFs for search and copy.

Recognize text in images and export as a Word document

Pick photos and a template to generate cool 3D showcase videos (fully local rendering)

Use the local LLM to review image content (risk levels + report export)

Local LLM tags each image (category + tag wall + CSV export)

Place screenshots into phone / tablet / laptop / monitor / frame / browser mockups with adjustable fit and background

Click / box / paint to select any object in an image and erase it with AI (local, one click)

Batch-recognize text in images (Chinese / English), copy / export TXT, fully offline

Translate text in images in one click: OCR Chinese/English and translate both ways, refill the image with the translation and export bilingual text

Extract tables from images in one click: recognize table structure to Excel/CSV/HTML with automatic cell boxes

Turn a single photo into 3D: MiDaS depth estimation generates a depth map, red-cyan anaglyph, wiggle 3D video and a 3D model (GLB)

Browse image and video assets and download them for local projects.

Search and download NASA images and videos, including the picture of the day.

Question bank, countdowns, answer cards and multilingual voiceover.

Words, phonetics, examples and read-along videos.

Food ingredients, allergens and nutrition cards.

Batch-convert CT/MR series to mp4 with window/level adjustment; patient info never enters the output

One pipeline: privacy masking + still-scene condensing + segments + compression for teaching/archiving compliance

Stopwatch timing, score marks and timed/score screenshots on training videos for one-click evidence

One-click sermon ASR + translation + bilingual subtitle burn-in for multilingual congregations, three steps for volunteers

Compare two videos side by side with synced slow motion, frame alignment, line and angle annotations, snapshots, and watermarked comparison exports.

Mark driving footage, fast-forward review, snapshot evidence and export segments for students

Apply fixed region templates to whole fleets, batch folder import, compliant face/plate masking, one-click report

For construction progress, calligraphy and painting: turn photo sequences into timelapse videos with portrait or landscape presets, date or artwork title labels, and side-by-side sequence comparisons.

Locate hook-up moments in a full day of footage by sound, cut segments with watermark and manifest, share to your fishing group

For exhibitions, weddings and coming-of-age celebrations: choose a scene preset, extract audio highlights, add intro/outro cards, a watermark and music, then export an event recap.

Mirror, speed and loop for practice; slice and watermark segments for studio distribution

Time-lapse sequences to paper-ready video: drift correction + deflicker + scale bar/timestamp/metadata overlays

Flag anomaly behaviors (barking/fighting/movement) and condense each day into one clip with shop watermark for owners

Ramadan/Eid/wedding/status templates: name replace + multilingual voice + video card

Sentence-by-sentence recitation with repeat gaps + Arabic subtitles (kid-read engine)

Turn recitation, music, narration or other audio into waveform and spectrum videos, with style, color, size and frame rate controls and batch export.

Mosque/rain/recitation ambience loops (sleep-video engine)

Season footage → 3-min highlight (youth-game-clip engine, Hudl-style)

Podcast/interviews → ASR-picked vertical clips (shorts-condenser engine)

Product images + CSV → Ken Burns album + multilingual voice (batch)

Click the map or import GPX to make a travel video with route animation and a title card.