New features, improvements, and a look at what’s coming next.
v3.0.0 New Improved
SmoothyApp 3.0: ShortsCuts, agentic editing and Community
SmoothyApp 3.0.0 is available for Apple Silicon Mac and Linux. Windows 3.0 follows shortly; Windows keeps 2.2.0 until then.
ShortsCuts: put Premiere effects, transitions and presets on keyboard shortcuts or your phone. Multi-actions, folders and keyframed presets. 6 keys free, unlimited with Smoothy Pro.
Agentic editing: connect Claude Code, Codex or any MCP agent to Smoothy’s tools. Leave notes on the frame, and approve every change. Part of Smoothy Pro.
Community: chat with other editors right inside the app. Free, guests welcome.
New icon and a refreshed sidebar.
Every tool that was free stays free. The macOS DMG and ZIP updater are Developer ID signed and Apple notarized. Linux has native x64 and ARM64 AppImage and .deb builds and remains experimental.
The real app up front. The interactive preview now includes ShortsCuts, agentic editing and Community.
Clear Free and Pro labels on every tool. Compare plans.
New Improved
Choose your Chat model
Chat now has a model switcher next to the Thinking toggle. Pick GPT-6 Luna, Claude Haiku 5.5, DeepSeek V4.1 Flash or Gemini 3.8 Flash; your choice is remembered. Luna and Haiku are the lowest-cost options, DeepSeek is close behind, and Gemini 3.8 Flash uses more credits and always runs with Thinking.
DeepSeek and Gemini moved to their newest releases. Picking a model never costs credits by itself, and Studio’s Admin setting can still turn Chat off.
New Improved
A note about SmoothyApp: free tools stay free, new Pro features
A note from Ali.
I build and support SmoothyApp on my own, and keeping everything completely free isn’t sustainable for me. I want to keep improving Smoothy for a long time, and that needs to pay for itself. So some new features will cost money.
Here is what that means for you:
Every tool that’s free today stays free forever. Multicam, captions, silence removal, Audio Cleanup, compression, Assets and the stock footage and audio libraries. No account needed.
SmoothyApp stays open source. The code stays public under the MIT license. Paid features run on trust: if Smoothy saves you time, Pro is how you keep it going.
Some new features cost money. The first one is ShortsCuts: put Premiere Pro effects, transitions and presets on keyboard shortcuts or your phone. You get 6 keys for free. Smoothy Pro unlocks unlimited keys.
Agentic editing with the Agent Bridge is part of Smoothy Pro, along with the full cloud AI toolkit.
I’ll keep it fair. No surprise paywalls on tools you already use.
New pages for ShortsCuts, agentic editing and Community
Three new SmoothyApp features, each with its own page:
ShortsCuts. Put Premiere Pro effects, transitions and presets on keyboard shortcuts. SmoothyApp also hosts a small local server, so your phone or tablet can be a macro deck over your own Wi-Fi. 6 keys are free; Smoothy Pro unlocks unlimited keys.
Agentic editing. Give Claude Code, Codex or another MCP agent Smoothy’s tools: multicam cuts, silence removal, audio cleanup, captions, images and titles, stock footage and music. It saves your agent tokens, asks before it changes anything and works alongside Premiere Pro, so you can make the final touches. Included with Smoothy Pro.
Community. A chat room inside SmoothyApp to ask questions and meet other editors. Free, and open to guests.
The home page, the features page and the menus now link to all three.
Fixed
Navigation lines up at every window size
The floating navigation bar now keeps its layout at any window width. On narrower desktop windows the GitHub, Discord and account buttons stay pinned to the right edge of the bar instead of drifting toward the middle, and the Product, Pricing and Resources links remain exactly centred.
The Dashboard button also reacts on hover like Sign in and the other header controls, with a soft background and a slightly darker border.
New
A brand kit for videos and articles
The new brand kit collects everything someone needs to show Smoothy in a video, review, tutorial or article.
It includes the black, lime and white wordmarks, the cup on its own, and official app icons for SmoothyApp, SmoothyREC and AI Studio — including the green board press variant. Every asset downloads as a ready-to-use PNG, with SVG versions alongside and the full set in one zip.
The page also lists the palette with hex values, the four Bunch weights, and short do-and-avoid rules for clear space, colour and app icon use.
Find it any time under Resources → Brand kit in the navigation or the footer.
v1.1.1 New Fixed
SmoothyREC 1.1.1: reliable saves and separate analytics
SmoothyREC has its own private Admin tab, separate from SmoothyEdit and Studio. Installer download starts, observed installations, app versions and recording/export actions are shown separately.
The updated recorder adds Settings → General → Share anonymous usage counts. Reports contain a random installation ID, app version and action ID; recordings, filenames, paths and account details are never included. Earlier activity cannot be reconstructed.
SmoothyREC 1.1.1 also improves recording recovery, repeated Stop and Save & Quit behavior, microphone compression, MP4 exports and picture-in-picture synchronization. The Apple silicon download is Developer ID signed and notarized.
v2.2.0 New Improved Fixed
SmoothyApp 2.2: Google sign-in and clearer downloads
SmoothyApp 2.2.0 is available for Apple Silicon Mac, Windows x64 and Linux.
Google sign-in: connect Studio through your browser, or keep using email. Free local tools still need no account.
Audio Library: each downloadable track has a visible download button, and the player offers larger Download MP3 and Send to editor actions.
Workspace: refreshed tool icons match the website preview.
Updates: a clear Update button starts the download; Restart & Install appears when it is ready. Release notes and Skip remain available.
Premiere Multicam: includes Windows 2.1.1’s correction for MXF timelines starting at frame zero or later, with CEP 1.5.14.
The macOS DMG and ZIP updater are Developer ID signed and Apple notarized. The Windows x64 installer is unsigned, so SmartScreen may ask you to confirm it before installing. Linux has native x64 and ARM64 AppImage and .deb builds. Linux remains experimental: packaging, startup and media decoding are checked; Resolve and GPU workflows still need testing on Linux.
The SmoothyApp page keeps its split introduction and platform download selector. Everything below it is shorter and easier to scan.
A new colorful toolkit starts with AutoMulticam — speaker-based cuts, J-cuts, nested clips, a new timeline and a clean result with no disabled clips. Then come silence removal, Audio Cleanup, captions in 100+ languages, compression, Assets, Stock Footage, Audio Library and optional Studio AI. Every card links to its own feature page.
The repeated app mockup and the long feature sections are gone. A compact local-processing band, a two-minute setup and four short answers replace them, with Premiere Pro and DaVinci Resolve support called out across the page.
Improved
Premiere Pro and DaVinci Resolve stand out on the homepage
The homepage introduction now sets Premiere Pro and DaVinci Resolve in a heavier, near-black weight, while the surrounding sentence stays muted. The editors are the first thing to read in that line, without adding color or another badge.
Improved
A compact SmoothyApp preview
The SmoothyApp page’s preview now starts with a compact icon sidebar, giving the workspace more room. Use the expand button to show the tool names.
v1.1.1 New
Meet SmoothyREC
SmoothyREC now has a home on SmoothyEdit. The new page explains the client-to-editor workflow, shows the recorder experience, and covers full-screen, window and area capture, cursor recording, camera choices, live audio levels, pause and resume, and the separate files delivered after every take.
Fixed the blank desktop approval page after Google sign-in. You can now review the connection, choose Approve, and return to SmoothyApp to finish signing in.
Improved
Follow Smoothy
You can now find Smoothy on X, Instagram, Threads and LinkedIn from the footer on every page. Each link uses its familiar brand icon with an accessible label.
Improved
Products, at a glance
The main navigation now has a Product menu that opens into a full-width panel. SmoothyApp, SmoothyREC and AI Studio each get a card with a short description and a preview of the workspace, so it is clearer what each one is before you click.
SmoothyREC joins SmoothyApp and AI Studio in the menu. Resources keeps the blog and changelog together, and the same product list appears in the mobile menu.
Improved
A personal touch on the homepage
A small cutout of Ali now points toward the free download button on the desktop homepage, tucked behind the app preview. Click the picture to visit alibahrawy.com. Mobile keeps its existing layout.
Improved
A clearer way into Smoothy
The navigation now includes a GitHub link to SmoothyApp’s public source and a Free download button that opens the app page. Sign in and Sign up are separate, clear choices, including in the mobile menu.
Sign-in and account-creation pages have a fresh cream-and-green design, clearer account links, and a reminder that the desktop editing tools don’t require an account. The sign-in form includes password visibility and authenticator/backup-code entry when two-factor authentication is enabled.
Google sign-in support is included, with availability shown on the form. Email and password remain available.
Improved
A clearer download from your account page
Download SmoothyApp now has its own button with a green download icon on the sign-in and sign-up pages. It opens the app page and makes it clear that the free editing tools need no account.
The sign-in page also has a simpler heading, with the extra “Your creative workspace” label removed.
Fixed
App previews load without the visual swap
Refreshing the homepage now shows the current app mockup immediately, instead of briefly displaying a different preview. The layout keeps the same size as the controls become interactive.
The caption and product-page previews also start with the matching tool and editor.
Improved
A download button that stays within reach
The homepage now shows a download bar at the bottom of the screen after you scroll past Download for free beside Studio AI. Scroll back to that button and the bar slides away.
The top navigation and mobile menu are simpler, with the Free download button removed. The bottom bar shows just the free/no-account note and download button, fits smaller screens and respects reduced-motion preferences.
The homepage’s Download for free and Studio AI (paid) buttons now lift gently on hover. Download buttons share a bouncing arrow above a stationary tray, including the bottom bar and platform downloads; the Studio arrow moves forward. Keyboard focus gets the same feedback, and reduced-motion preferences disable the movement.
Improved
A clearer SmoothyApp introduction
The SmoothyApp page now pairs its name with mint, purple and blue labels for SmoothyApp, Premiere Pro and DaVinci Resolve Free. The repeated NEW Resolve announcement has been removed from this page.
On desktop, the app preview sits beside the introduction. A sliding macOS / Windows / Linux selector shows one download action and the matching format, including the experimental Linux note. The layout stacks on smaller screens, and the selector supports keyboard navigation and reduced-motion preferences.
The selector automatically starts on the visitor’s desktop operating system. You can still switch platforms manually; detection runs locally in the browser.
The selected download action is now larger, with a brighter green finish, deeper lift and a soft passing shine so it stands out immediately.
Improved
A more visual look at the free toolkit
The homepage brings Multicam, local captions, Audio Cleanup and Premiere Pro / DaVinci Resolve Free together in colorful cards, with shorter labels and editing-focused visuals: camera tracks and a finished cut, a timed caption cue, and original/voice waveforms.
Explore each tool from its card. The editing tools remain free, with no account needed.
Removed the repeated explanatory lines below the homepage app preview for a cleaner layout.
A subtle blue gradient adds depth to the opening section, from a very light top to a muted shade beneath the app mockup.
Floating icons now include Audio Cleanup, image upscaling, compression, background removal, AI Photos and DaVinci Resolve around the app preview.
v2.1.1 Fixed
Windows 2.1.1: Multicam and Settings fixes
SmoothyEdit 2.1.1 for Windows fixes two issues reported after the 2.1 release:
Premiere Multicam: fixes “Premiere could not move camera video safely” at frame 0 or a clip’s timeline start when the highest video track contains a selected camera, including three-camera MXF timelines. The temporary track is now appended correctly, with extra checks that existing camera tracks stay in place. Multicam still edits a duplicate and preserves continuous audio and clip effects.
Settings: keeps the Settings header and close button below the native Windows title-bar controls, including at the minimum window size. The options scroll while the header stays visible.
Update through Settings → Check for Updates, or download the Windows installer. Restart Premiere and reopen the SmoothyEdit panel after updating, then run Multicam from your original sequence.
This is a Windows patch. The existing Mac and Linux 2.1.0 downloads remain available.
v2.1.0 New Improved Fixed
SmoothyApp 2.1: DaVinci Resolve and Audio Cleanup
SmoothyApp 2.1 adds two reasons to open the app before your next edit: DaVinci Resolve Free support and Audio Cleanup. The local tools stay free, with no account or Studio credits.
DaVinci Resolve Free
Choose Premiere Pro or DaVinci Resolve in the editor switcher. Resolve uses a local Smoothy Connector started once per session from Workspace → Scripts. No Resolve Studio licence or external scripting connection is needed.
Multicam and Silence Removal read your current Resolve timeline, save the result in SmoothyEdit Assets → Resolve and send it back as a new timeline.
Captions can read the loaded timeline or a media file, then send the SRT to the Media Pool.
Assets, AI Photos, Stock Footage and Audio Library import PNGs, MP4s and MP3s into the Media Pool.
Shorts markers are added to the loaded Resolve timeline.
Generated timelines carry the cuts, source timing and selected microphone channels. They do not copy grades, effects, fades, automation or mixer processing, so review the imported edit. Resolve’s File menu remains the manual fallback if an action is refused.
The new Audio Cleanup splits a recording into exact Speech and Music tracks. Noise stays with the music rather than becoming a third track. Turn on Enhanced to clean the speech and remove music and noise completely; the enhanced speech gets a Less / More preview control, while Original plays the exact split unchanged.
Save the Speech and Music WAVs from Original, or the enhanced speech from Enhanced. Preview levels affect the enhanced preview only, not the saved WAVs.
Setup is a one-time local engine and model download. It needs Python 3.12 or uv and an internet connection; processing then works offline with automatic GPU selection and CPU fallback. Original Speech and Music each have Solo and Mute controls, and progress reports completed processing chunks. Audio Cleanup does not upload your recording, use Studio credits or place files on a timeline.
SmoothyApp now builds for Linux (AppImage and .deb, x64 and arm64). The same free local tools work on Linux — with DaVinci Resolve as the supported editor, since Premiere Pro does not run there. The Premiere panel is not installed on Linux.
Linux builds are experimental. Native packaging, app startup and media decoding are checked; Resolve and GPU workflows still need testing on Linux.
A cleaner workspace
The built-in Moroccan Darija choices are MoulSot v0.3 (recommended) and Whisper Small Darija (DoRA) as a compact alternative. Switching languages restores the full built-in model list.
Settings → Caption models opens your downloaded models folder. Add compatible whisper.cpp GGML .bin files for any language and refresh to use them locally. Custom models stay available across languages and use your selected spoken language.
The AI Photos model picker now offers 21 choices across 11 companies, with Budget and Premium filters and a logo for every company.
The tools sidebar has a subtle scroll hint and no visible scrollbar.
The “Your workspace” heading stays on one line while the sidebar animates.
Studio, AI Photos and Chat show their full interface to visitors with a clear Sign up for free invitation and 100 AI credits every month for signed-in free accounts.
On Windows, the native minimize, maximize and close controls now sit in SmoothyEdit’s existing top bar.
Audio Cleanup’s startup decoder lookup, progress panel and error guidance are also fixed for this release.
Download SmoothyApp 2.1 for Apple Silicon Mac or Windows x64 from the app page. The Mac build is signed and notarized and is offered through the app’s updater; Windows 2.1 is available as an unsigned installer and through the app’s updater. Linux is a fresh install (AppImage or .deb).
v2.1.0 Improved Fixed
Audio Cleanup: GPU acceleration, Solo, and real progress
Audio Cleanup can use NVIDIA CUDA, Windows DirectML for AMD and Intel GPUs, and Apple Metal on Apple Silicon. The local engine installs the matching runtime during setup and falls back to CPU if GPU processing cannot finish. CUDA and CPU processing have been tested; DirectML and Metal acceleration are experimental. Linux AMD acceleration is not included in this update.
Each original Speech and Music track now has Solo and Mute controls. Click Solo to hear that track on its own; click it again to return to both tracks. Playback stays synchronized, with one shared pause and seek control. Original retains its exact levels, and saved WAVs are unaffected by listening controls.
Processing progress reports actual completed chunks, voice windows and output blocks. Downloads show transferred bytes when the size is available. Model loading and installation show their current stage without an invented percentage or finish-time estimate.
Included in SmoothyApp 2.1 for Mac. Other platforms receive these changes as their 2.1 builds are published.
Improved
A simpler way around SmoothyEdit
Find the changelog in the navigation, open your dashboard when signed in, or sign up with a sign-in link for existing members. The homepage has one Free app link beside AI Studio, shorter Multicam and captions sections, a colorful Studio tool grid and a refreshed Discord invitation.
The homepage Free app button opens the SmoothyApp feature page.
Improved the Windows download button contrast on the dark homepage download section.
The homepage and SmoothyApp hero now highlight DaVinci Resolve Free support, linking to the connector workflow and making clear that Resolve Studio is not required.
v2.1.0 Improved
Audio Cleanup: exact Speech and Music, clearer Enhanced view
Audio Cleanup now works as a direct two-track tool.
Choose a recording and SmoothyApp separates it into Speech and Music. Noise stays in the Music track, so there is no separate Background track to manage. Original plays both tracks together at unity with no level changes, which keeps the exact separation faithful to the recording.
Turn on Enhanced to clean the speech and remove music and noise completely. Only the enhanced Speech card remains, with a Less / More control for its preview. The slider does not change the saved WAV.
Save the exact Speech or Music WAV from Original, or the enhanced speech from Enhanced. The source file stays untouched, and the first separation still performs the one-time local engine and model setup.
The desktop AI Photos picker now has 21 choices across 11 companies, with at most two per company. Older OpenAI and Google entries have been removed from the picker, and every company has a logo.
Budget and Premium badges and filters make the options easier to compare. OpenAI keeps the newer Flare and Sunburst models, labeled Fast and Precision because their listed rates match. Tencent has one preview option.
Credit estimates, supported image sizes and reference limits continue to follow the selected model.
Fixed
Smoother sidebar transitions
The desktop app keeps “Your workspace” on one line while the sidebar changes width. It hides during collapse and fades in once there is room, avoiding stacked text and the sudden jump during expansion. Reduced-motion preferences are respected.
Improved
A cleaner tools sidebar
The desktop tools sidebar hides its scrollbar while keeping natural scrolling. A subtle shadow at the bottom hints that more tools are below, then disappears when you reach the end or the list fits. It also follows search results, folded tool groups and window or sidebar resizing.
Improved
Clearer Studio signup invitation
The desktop app removes the redundant “Input” label above Studio’s editor, subtitle, audio/video and YouTube source choices.
The monthly free-credit offer now uses a light lavender callout and a filled purple Sign up for free button across Studio, AI Photos and Chat. Free and 100 AI credits remain bold, and the button opens account creation directly.
Improved
100 free AI credits every month
Studio, AI Photos and Chat stay visible to visitors, with a clear invitation: Sign up for free and get 100 AI credits every month. The sign-up button opens account creation directly, and the same message appears in the form. The free offer and credit amount are bold in both places so they are easy to spot.
Signed-in free accounts can use their allowance for eligible Studio tools, AI Photos and Chat. Credits refresh every 30 days. Visitors can explore the interface, while generation requires an account and a remaining balance. Existing Pro-only tools keep their plan requirements. Local editing stays free and uses no cloud credits.
No extra credits or historical usage are created.
Improved
A cleaner Windows title bar
On Windows, the native minimize, maximize/restore and close controls now sit inside SmoothyEdit’s existing top bar, removing the extra system title-bar row. The controls follow the active tool’s bar color, with space reserved for them even in smaller windows. Native window behavior is retained, and the Mac layout is unchanged.
v2.1.0 New
Audio Cleanup: separate speech from music and noise
Audio Cleanup joins the free Editing tools. Choose an audio or video file and SmoothyApp separates it into two exact tracks, with noise kept in the music:
Speech is the voice from the recording.
Music contains the music bed, room tone and noise outside the speech.
Turn on Enhanced to clean the speech and remove music and noise completely. Only the enhanced speech plays, and the Less / More control appears for its preview. Original has no level controls: the two separated tracks play together unchanged.
The first separation sets up an isolated local engine and downloads the UVR DeNoise Lite and MDX-Net models. It needs Python 3.12 or uv, an internet connection and several hundred megabytes of disk space. After that, audio processing works offline on the CPU and does not use Studio credits.
Compare Original and Enhanced, then save the exact Speech or Music WAV, or save the enhanced speech. The source file is never modified. A clear progress panel shows loading, separation, cleanup and output checks with elapsed time; you can cancel while it runs, and an error stays visible with repair guidance.
The mint-and-lime preview mixer has one play/pause and seek bar and an Original / Enhanced comparison switch. The Speech and Music cards stay in place; the enhanced view shows only Speech with the Less / More preview control. Downloads keep the separated WAVs; preview levels do not change the files.
The input stays simple: a short explanation and a file picker. Separation starts when the file is ready, and switching versions or adjusting the enhanced preview reuses the finished tracks.
Longer WAV previews show their duration and support seeking without loading the entire recording into memory.
Audio Cleanup does not place results on a timeline. Import the WAVs into Premiere Pro, DaVinci Resolve or another editor yourself. Separation quality varies by recording, and artifacts can remain in difficult material.
SmoothyApp now works with DaVinci Resolve Free. Choose Resolve in the editor switcher, install the local Resolve helpers once, then start Workspace → Scripts → Smoothy Connector each Resolve session. No Resolve Studio licence, paid plugin or external scripting port is needed.
The same editor selection now follows the tool. Premiere Pro keeps its bundled panel; Resolve uses the local connector for:
Auto Multicam and Silence Removal, which read the current Resolve timeline, save the result in SmoothyEdit Assets → Resolve and send it back as a new timeline.
Captions, including reading a loaded Resolve timeline and sending the SRT to the Media Pool.
Assets, AI Photos, Stock Footage and Audio Library, which import PNGs, MP4s and MP3s into the Media Pool.
Shorts markers, bound to the loaded native timeline, with existing markers preserved.
Captions and Studio can use a Resolve timeline as their source. Smoothy copies known trims, offsets and microphone channels; Resolve mixer processing and effects are not included.
Generated timelines carry the edit Smoothy makes, not your finishing: grades, transforms, Fusion and clip effects, fades, automation and transitions are not copied. Decompose nested and multicam clips and remove retiming before exporting. If Resolve refuses an action, Smoothy keeps the saved XML, PNG, MP4 or SRT and you can import it from Resolve’s File menu.
A native receipt confirms each import, and waiting requests can be cancelled. Start the connector from the Scripts menu once per session; restarting SmoothyApp reconnects to the running Resolve helper.
The article discusses the work behind dependable creative tools, the risks of rushed replacements, shared project standards and sustainable funding for both established companies and independent alternatives.
The article includes a logo-focused HTML/CSS cover with Adobe and ArtCraft, bold red and blue accents and the question “The end of Adobe?”, also used as its social sharing image.
New
Quick app downloads in the dashboard
The Studio dashboard now shows a Download the app panel in the bottom-left corner, with dedicated macOS and Windows buttons that link straight to the current installers.
Keep the desktop app handy without leaving your analysis workspace.
v2.0.0 New Improved
SmoothyApp 2.0 is here
SmoothyApp 2.0 is a major desktop release. The local tools stay free with no account, and the optional cloud Studio is clearer than ever.
AutoMulticam switches between speakers on duplicated timelines, with nested-clip support and preserved audio, clip effects and keyframes.
Captions add a multilingual engine, Arabic support with an accuracy note, drag-and-drop audio or video input, and SRT export for DaVinci Resolve Free.
Assets gains local image tools — background removal and image upscaling — plus the SVG importer.
Stock Footage and the Audio Library search, preview, download and import footage and music into Premiere, with source and license notes.
A refreshed Studio workspace unifies Shorts, writing and planning tools behind one input.
Optional AI Photos and Chat use your Studio credits, with reactions, reference images, attachments and per-account cloud history.
A cleaner Settings screen, feedback and feature-request links, and an in-app update notice.
The local tools run on your machine without an account. Studio features are optional and use the shared $5/month, 2,000-credit plan. Existing installs will be offered the update automatically.
The sidebar editor indicator now switches between Premiere Pro and DaVinci Resolve Free, with editor logos available when the sidebar is collapsed.
Cancel Silence Removal or Premiere Multicam during preparation and analysis. AI Photos also offers Stop for single images, and Compressor waits for canceled work to stop before starting again. Edits already submitted to Premiere finish safely.
Windows now uses the bundled Bunch typeface throughout the interface, matching the Mac design, with a consistent Lucide SVG set for sidebar tools.
Improved
GPT Image 2.5 Flare is the AI Photos default
AI Photos now starts with GPT Image 2.5 Flare, the fast everyday generation and editing model in OpenAI’s latest GPT Image family. It appears first in the model picker and is also used when an image request omits the model.
All other image models remain available. The developing v2 desktop app uses the same default; desktop v2 remains unreleased.
Improved
Cloud Chat History for the v2 preview
Chat History in the developing v2 desktop app uses account storage on the server, so saved conversations can follow you to another device. Reopen or delete a conversation from History. Each account keeps its 30 most recently updated conversations.
Completed conversation text and the Thinking preference are saved. Attached files and images are not retained. Existing histories from earlier previews transfer when you next use Chat History; local copies stay in place until the transfer succeeds. History actions use no AI credits.
The server stores Chat History in Cloudflare D1. This is available to the local v2 preview; desktop v2 remains unreleased.
Improved
A shorter homepage, with Studio Pro in view
The homepage now leads with Auto Multicam. The app is free, with no account and no credit card. Captions cover 99 languages, including Arabic. SVG files can be converted without Premiere. DaVinci Resolve users can import an SRT today, and a Resolve plugin is coming soon.
Studio Pro stays optional at $5/month. Best Shorts, image generation, and the other cloud tools are on that plan, and new Studio tools join it as they ship.
The homepage mockup shows the newer app sidebar. Downloads still serve the current public Mac and Windows installers.
Improved Fixed
More AI Photos models and matching settings
AI Photos supports the shared catalog of 44 image models, including GPT Image Mini, Nano Banana, FLUX, Seedream, Qwen, Microsoft, Krea, Recraft, Grok and Riverflow models. GPT Image Mini is the default.
Shapes, resolutions and reference-picture limits now match the selected model. Requests without explicit settings choose supported defaults. Uploads retain the six-picture limit, with fewer references for models that require it; models without reference support accept text prompts only.
Private Admin usage also includes the Studio subtitle-source import row, including when its count is zero. Existing usage history and credit billing are preserved.
The developing v2 desktop app uses this shared server catalog. Desktop v2 remains unreleased.
Improved Fixed
Cloud image history for paid members
Paid members can keep their 30 newest generated or edited images in cloud history, up to 100 MB total. Older images are deleted automatically when either limit is exceeded, including favorites. Individual saved images can be up to 20 MB. Download images you want to keep permanently.
Free members can still generate and download images. Cloud image history requires a paid membership; images become unavailable when that membership ends.
Image files use Cloudflare R2, with history metadata in Cloudflare D1. Admin now reports measured database and file sizes and distinguishes unavailable readings from empty storage.
Improved New
A clearer home for SmoothyApp and its editing tools
The website keeps its colorful style and interactive app previews, with a simpler path to the free Mac and Windows downloads.
AutoMulticam leads, followed by local captions, including Arabic, and the rest of the free toolkit.
A dedicated guide explains how to export SRT captions for DaVinci Resolve Free. The native Resolve plugin is still upcoming.
Discord is visible in the header and has a community section for questions, edits and feedback.
Studio explains its optional $5/month plan, credits, Shorts suggestions, writing tools, AI Photos and Chat.
Focused feature pages and six new practical guides cover the expanded workspace, with links between tools and workflows.
The app’s local tools remain free without an account. The interactive website previews use sample content and do not run the real tools.
Improved Fixed
Website security and accessibility improvements
The website now uses a Content Security Policy and additional browser security headers. Login, signup and Studio include a primary page heading, and helper text in the interactive app preview is easier to read.
Browser failures can now be diagnosed through our existing hosting logs. These reports contain only an error category, a page category and bundled-code coordinates. They exclude messages, prompts, account details, full URLs and query strings, and respect browser privacy signals.
v2.0.0 Fixed Improved
Arabic caption repetition fix and file drag and drop
The local desktop preview prevents previously guessed text from conditioning later audio windows. This fixes a reproduced failure where the Arabic Base model repeated one phrase through much of a recording’s second half. Transcription segments also split at word boundaries, preventing Arabic words from being broken into separate caption words. Audio preparation now reports conversion failures instead of passing an unprepared file to the engine. Caption editors automatically follow the text’s writing direction.
Drop an audio or video file anywhere in the Captions panel, or click the drop area to choose a file. Valid files switch the source to Audio / Video File. Unsupported, empty or multiple-file drops leave the previous input in place.
Arabic paired with Tiny or Base shows an accuracy note and a shortcut to Large v3 Turbo. The larger model downloads once when generating; changing a model never starts transcription. Multilingual support alone does not guarantee accurate dialect recognition.
This desktop preview is local and has not been published.
v2.0.0 Improved
A simpler image composer and a Reactions side panel
The local SmoothyApp v2 image composer puts Image refs and Reactions on the same row and removes the extra Image heading and options button. Reactions opens a full-height side panel with expression presets, your reference picture, and optional subject details.
Image refs appears only while empty. Once you attach or select a reference, its picture replaces that tile. Remove the last reference to show the empty tile again, or click its thumbnail to choose more reference pictures.
The model selector now includes each provider’s logo. An approximate credit cost beside Send updates with the model, resolution, reference inputs and selected reaction count. Final credits depend on actual usage; configurations without a published price show that the estimate is unavailable.
This is an unpublished desktop v2 preview. Image generation, editing, reaction batches, shared history and successful-action usage counts keep their existing behavior.
v2.0.0 Improved Fixed
Cleaner desktop Settings and easier feedback
The upcoming desktop preview has a smaller Settings header and a centered layout that stays readable when the app fills your screen. Long update messages wrap inside their section, and action buttons adapt to narrower windows.
Give us feedback, request a feature or report a problem from the new feedback section. Each action opens an email draft for you to review and send. Community now includes SmoothyEdit on X, alongside Ali’s existing personal account.
Local preview packages show that automatic updates are unavailable instead of failing on a missing update configuration. Published app builds retain their update checks and your choice of when to download, install or skip a release.
This desktop preview is local and has not been published.
v2.0.0 Improved
One input for every desktop Studio tool
The upcoming desktop Studio uses one bottom input for Shorts, Condense, Hooks, Titles, Descriptions, Thumbnails, B-roll, Social, Blog and SFX. Choose your tool from ten equal-sized buttons in two rows at the top.
Use the visible input slider to choose Premiere, Subtitles, Audio/Video or YouTube. Upload TXT, SRT or VTT subtitles through the file picker. Premiere and local audio/video create subtitles on your device using the app Captions engine and settings. Prepared subtitles are reused across tools, and your selected input tab stays selected. Generating ideas still uses Studio credits.
Results now fit the tool: Shorts cards with time ranges, separate description sections, individual titles and hook cards, thumbnail briefs, timed editing suggestions, social posts and readable articles. Edit fields, copy a section or the full result, save text, refine with AI or reopen history. Your input and each tool’s draft stay available when switching tools.
This desktop preview is local and has not been published.
Improved
Arabic captions guidance
Removed the old Multicam announcement from the homepage, SmoothyApp and Multicam pages, and its duplicate in the 1.5.1 article.
A dismissible Arabic captions notice now appears in SmoothyApp’s Captions section and the local caption guide. It recommends Arabic with Large v3 Turbo, explains the limitations of Tiny and Base for dialects, and keeps the Discord, X and Instagram support links available.
The matching desktop notice is part of the local v2 preview. This website update does not publish a new desktop release.
Improved
A simpler desktop sidebar
The upcoming desktop version groups Studio, AI Photos and Chat in one expanded AI Tools menu, with Studio first. Each shows a Credits badge. Chat has its own coral accent and message icon to make it easier to spot beside AI Photos.
Assets now sits under Editing. The Library menu keeps Stock Footage and Audio Library.
New Improved
Automatic Multicam, Local Captions and a Colorful Home
The homepage and plugin page put automatic multicam switching first, followed by local captions. The familiar pastel colors, floating tool icons and interactive app mockup return, with direct Mac and Windows download buttons.
The caption page shows the source, model settings and editable caption cues. The SmoothyApp workspace page brings the rest of the toolkit together. New guides cover preparing a speaker-based multicam edit, generating local subtitles and moving through the app.
Local editing tools are free and work without an account. Optional Studio, AI Photos and Chat use cloud services, an account and credits. Website demos use sample data; processing and Premiere actions happen in the desktop app.
Improved
Simpler Chat controls
Admin → Models now includes one Chat model setting for all users, with Luna as the default.
The upcoming desktop version removes the Chat model selector and extra welcome text. Settings keeps an optional, empty system prompt field with Save and Clear.
Fixed
Pages stay visible while loading
The website now keeps its heading, text and buttons visible as soon as they appear. A delayed animation previously hid them and faded them back in, making the page look like it had reloaded.
Scroll animations still work for sections below the screen. Content already visible when those animations finish loading stays in place, including when you scroll early or open a section link. Reduced-motion preferences keep the page static.
New Fixed
Download YouTube transcripts
In Studio, choose YouTube, paste a video link and click Fetch. When the transcript is ready, choose Download transcript to save its timestamped text as a TXT file. The transcript stays loaded for Shorts, titles, descriptions and your other tools.
Downloading uses the transcript already loaded in your browser, without fetching captions again or spending AI credits. Videos must have an available transcript. Free and Studio Pro accounts can use the existing YouTube source.
v2.0.0 Improved
Desktop preview: a cleaner image composer
AI Photos gets a spacious rounded composer with an Image refs tile, shape and resolution controls beside the model, and your Studio credit balance beside Send. The model menu has larger provider tiles, descriptions, search and Fast, Low cost and 4K filters. Resolution choices follow each model’s supported sizes.
Credit reminders, keyboard hints and routine success messages such as “PNG saved” are removed from the footer. Errors and reference-limit warnings remain visible. Existing image generation, edits, Reactions, history and export actions work as before.
This desktop update is a local preview. Public app downloads remain unchanged.
v2.0.0 New Improved
Desktop preview: Chat and visible Assets image tools
The upcoming desktop version adds Chat beside AI Photos, with a bottom message composer and a compact custom model menu. GPT-6 Luna is the default; DeepSeek V4.1 Flash and Gemini 3.5 Flash are also available. Luna and DeepSeek offer Thinking or Non-thinking, with Non-thinking selected by default. Gemini requires Thinking. Replies use Studio credits, including reasoning tokens when enabled. The model selector sits beside Send. A + menu lets you attach images, text-based PDF, DOCX and text files, preview and remove them, then send them with your message. Attaching reads files locally and does not spend credits. You can continue a conversation, stop a reply, start a new chat, and copy or save its text.
Menus and controls now use closer, more defined shadows.
Your Chat messages appear on the right and AI replies on the left. Send smoothly changes into Stop during generation. Loading dots show when a reply is arriving, and real streamed replies appear word by word with a gentle fade. Stop keeps the words already shown; incomplete replies stay out of follow-up context. Reduced motion removes the animation.
The Chat composer has a cleaner footer: credit-use reminders, keyboard hints and routine status messages are removed. Errors appear only when needed.
Thinking now uses one compact on/off toggle. Turn it off for faster replies or on for reasoning. Gemini keeps the toggle on because that model requires Thinking.
Settings adds optional Natural writing for Chat, with editable instructions, Save and Reset. The default combines a conversational tone and concrete examples with “I am” and “you are,” short paragraphs, numbered steps and no dash punctuation. Other contractions such as “don’t” and “can’t” are allowed. Instructions are saved on your device and included with your next Chat message only when enabled. Chat displays bold emphasis and numbered steps as readable formatting.
Assets now shows Remove background and 2×/4× Upscale before you add an image. Both tools run free on your device and become available once an image is loaded.
This desktop update is a local preview. Public app downloads remain unchanged.
Improved
Affordable model choices for text chat
The text chat service now supports GPT-6 Luna, DeepSeek V4.1 Flash and Gemini 3.5 Flash, with Luna as the default. These choices support the upcoming desktop Chat workspace. Gemini Flash uses more credits than Luna and DeepSeek.
Conversation context is preserved across follow-ups, with bounded message sizes and reply lengths. The service rejects unsupported model choices and keeps provider credentials on the server. Private Admin usage reporting distinguishes accepted chat requests from completed desktop replies, copies and saves.
Improved
Chat response modes
Chat now supports explicit Thinking and Non-thinking requests with GPT-6 Luna and DeepSeek V4.1 Flash. Non-thinking is the default for these models; Thinking uses low effort. Gemini 3.5 Flash requires Thinking.
Responses remain limited to the same budget model list and 2,048 output tokens. Studio credit billing includes reasoning tokens when enabled. Mode selection itself does not consume credits or add feature usage.
New Improved
Chat file and image support
Chat now accepts images and document text with Luna, DeepSeek V4.1 Flash and Gemini 3.5 Flash. Files can be included in follow-up conversations while retaining the existing Thinking and Non-thinking controls.
The upcoming desktop preview reads PDF, Word and text documents locally and prepares images before sending. Files are included only when you send a message. Context limits and the same budget model list remain enforced; images and document text use Studio credits when sent. No premium-model fallback or additional file-parser service is used.
New Improved
Chat writing preferences
Chat now supports optional writing preferences with the same budget models and Thinking controls. Instructions are included only when enabled and apply to the next message. Replies keep the existing Studio credit billing and response limits.
The upcoming local desktop preview adds Natural writing in Settings, with editable instructions, Save instructions and Reset to default. The default combines a conversational tone and practical examples with full forms such as “I am,” short paragraphs, numbered steps and no dash punctuation. The preference starts off and saves on your device. Public desktop downloads are unchanged.
v2.0.0 Improved
One AI Photos workspace, with a chat-style composer
The upcoming desktop AI Photos workspace has one sidebar entry and a prompt box at the bottom. Attach reference pictures with +, paste or drop, then create an image or describe an edit.
App-styled menus replace system dropdowns for models, shape and resolution. Choose from 15 models, including FLUX, Seedream, Grok and Riverflow. Model search and supported options help you choose. Reactions has its own button with all 18 presets and optional extra instructions. The other tool actions, including prompt enhancement, are removed from this workspace.
Pictures and prompts appear together in a conversation. Reuse a result, save a PNG, copy an image or send it to Premiere. Shared history, favorites and deletion remain available.
Generation, editing and reactions continue to use Studio credits. The composer shows your balance before sending; the final charge depends on model, size and API usage. Attachments, previews and saving are free. This desktop version is being tested locally and has not been published.
v2.0.0 New Improved
A bigger Assets preview and local image tools
Assets replaces the upload card with a larger preview when you add an image. Replace, paste and clear controls stay next to the preview.
Free local background removal uses BiRefNet, and image upscaling uses Real-ESRGAN at 2× or 4×. The models download once and work offline afterward; your images stay on your computer. Progress, cancellation and Restore original let you try the tools before saving a PNG or sending the selected image to Premiere.
v2.0.0 Improved Fixed
One Studio workspace, with buttons for every tool
The upcoming desktop Studio has one sidebar entry. Ten buttons choose Shorts, Condense, Hooks, Titles, Descriptions, Thumbnails, B-roll, Social, Blog and SFX.
Fixed the Studio sidebar link failing to open when the tool search is empty. It now opens directly and remembers your selected tool; searching for a tool and pressing Enter also opens it.
The draft tools share a transcript box at the bottom. Use + to upload a transcript, reuse Captions or Shorts, or load a YouTube transcript. Switching tools carries your transcript and keeps each tool’s editable draft and refinement request. Options appear when the selected tool needs them.
Shorts keeps its Premiere, transcript, audio/video and YouTube sources, multiple clips or Best Part, saved history and Premiere markers. Studio credits, Pro access and per-tool usage counts remain in place. Selecting buttons does not spend credits.
This desktop version is being tested locally and has not been published.
New Improved
More image models in AI Photos
AI Photos now offers 15 image models. New choices include FLUX.3 Image, FLUX.2 Pro, Flex, Max and Klein, Seedream 5.0 Flash and 4.5, Grok Imagine Image 2.0 and Riverflow V2 Fast.
The available canvas shapes, resolutions and reference limits follow the selected model. Generation and edits use Studio credits, with image-based API charges included in the final cost. Selecting a model or attaching a picture does not spend credits.
The private Admin usage table includes feature totals and verified Free, Paid and Anonymous request counts. Each accepted image request counts once, separately from credit billing. Newly recorded activity starts with this update; no earlier Studio usage is invented. Desktop counters appear as supported app builds report them.
New
SmoothyEdit on Product Hunt
The homepage and footer now include our official Product Hunt badge. Visit the SmoothyEdit listing to follow the released desktop app’s launch and share feedback.
Improved
Product Hunt badge stays in the footer
The Product Hunt badge now appears only in the footer, keeping the homepage focused on the editing tools and download buttons.
New
Email verification controls for admins
User Management now shows whether each email is verified, along with its verification date. Admins can verify an unverified email from the user list or user details.
Manual verification also invalidates that account’s pending verification links. Repeating the action preserves the original verification date.
Improved Fixed
Smaller, colorful Studio tools with clearer editing guidance
Studio’s tool buttons now use four compact columns on wider screens, with a distinct color for each tool and comfortable touch targets on smaller screens.
Shorts markers identifies candidate ranges and sends markers to a connected Premiere timeline. You make the cuts, reframe and export the finished video.
Hook ideas suggests opening moments and wording. You choose the opening and edit it into your video. The results explain this too.
Condense plan, thumbnail, B-roll and sound-effect controls describe the suggestions they provide.
Removed Add Music from Studio and its customization menu. Existing saved preferences skip that retired tool. The free desktop Audio Library remains available for choosing music.
Account credit checks stop further cloud AI calls after the balance is exhausted. Repeated payment events no longer refill spent credits; previously issued balances keep their normal reset date.
New
Daily installation growth in Admin
Admin → Usage now shows new installations per day, with 7-, 14-, and 30-day views, platform totals, a seven-day average and a daily numbers table.
Dates use Cairo time. Today is marked as incomplete and compared with yesterday after the same elapsed time; averages and weekly comparisons use completed days. Earlier dates without recorded history are not filled with invented activity.
The chart uses existing anonymous first app reports. It counts each installation once, independently of download requests, launches and app updates. No new desktop release is required, and the data remains private.
New Improved
Feature usage across the app and Studio
The private admin usage dashboard now lists feature activity with all-time and last-30-day counts. Studio requests include separate Free, Paid and Anonymous totals, and analysis requests count once even when they require multiple AI passes.
Desktop builds with the expanded tracking report Stock Footage, Audio Library, caption exports and Premiere imports alongside existing tool counters. Desktop v2 also has separate AI Photos actions for image tools, saved PNGs, clipboard copies, full previews and Premiere imports. Native Studio drafts, refinements, TXT saves and clipboard copies have separate counters. Retired support actions retain their earlier counts when available. Newly tracked actions start counting when their instrumentation is available; earlier untracked activity is unavailable.
Local Assets cutouts, upscales and decoded image previews have separate counters. Processing counts verified completed images; canceled and failed work is excluded. These free local tools do not use Studio credits.
Improved
Studio Pro for $5 a month
Studio Pro is now $5 USD per month, with 2,000 AI credits every 30 days.
Free accounts still receive 100 AI credits every 30 days.
Previously issued credits remain available until their normal reset; the new allowance applies to new balances and subsequent resets.
Shorts provides timeline markers and hooks provides opening ideas. You choose and make the edit.
New
Desktop app version analytics
Admin → Usage now groups anonymous desktop installations by their latest reported app version, with installation totals, percentage share and activity over the past 30 days.
The existing app telemetry already reports versions, so this works with released builds without requiring an update. Each installation is counted once and moves to its new version on its next report. Offline installations retain their last reported version; installations with telemetry disabled are unavailable. These private counts represent installations rather than unique people.
Improved
Simpler site navigation
Removed the installation and revenue tab below the navigation across the site. These totals are no longer shared through a public stats endpoint; analytics remain available privately in Admin.
v1.5.1 New Improved Fixed
SmoothyApp 1.5.1: libraries and the Multicam fix
SmoothyApp 1.5.1 is available for Apple Silicon Macs, signed with Developer ID and notarized by Apple. Download for Mac or read the GitHub release notes.
Fixed
Multicam: source clips and nested sequences work on a duplicate of your original timeline. The chosen angle stays on the top selected camera track, with the reverse footage visible and selectable underneath for fine-tuning. Existing clip effects and continuous microphone audio are retained.
Viewing another sequence during analysis no longer interrupts the captured job. Microphone exports use an app-created job folder, avoiding protected macOS temporary folders.
The original timeline stays intact. Failed or incomplete camera edits are reported for review instead of being marked complete. Start from your original timeline and review both speakers and audio sync before using the result. Multicam remains beta.
New and improved
Stock Footage: search Pixabay, Commons, Internet Archive and NASA, preview shots, save MP4s and import into Premiere’s Project panel.
Audio Library: preview artist-made music, filter by title, artist, genre or mood, keep Favorites and Saved MP3s, and explore Staff picks. Local favorites work without an account; anonymous favorite sharing can be switched off.
Licenses & credits: retain source notes and supplied attribution. The music archive is unofficial and does not supply verified track licenses; check the track in YouTube Studio before publishing.
Community: LinkedIn and personal website links in Settings, plus an Instagram shortcut beside Discord.
The website now includes the new library page and article, an interactive workspace demo, the compact dismissible Multicam notice, and installation/revenue totals beneath the navigation.
Windows: the current installer and update files remain 1.5.0 until the Windows 1.5.1 build is ready. The new libraries and Multicam fixes require 1.5.1.
v1.5.1 New Improved
1.5.1 preview: more of your edit in one app
The homepage and SmoothyApp page now preview the two libraries coming in 1.5.1:
Stock Footage: search Pixabay, Commons, Internet Archive and NASA, preview a shot and save an MP4 or send it to Premiere’s Project panel.
Audio Library: browse an unofficial YouTube Audio Library archive, preview artist-made tracks, keep Favorites and start with Staff picks selected by the team.
Updated mockups: explore both library tabs, filter sample shots and music, try Favorites and Staff picks, and see the import actions. These previews use sample media and illustrative picks.
A wider workspace: the SmoothyApp introduction sits above a wide interactive mockup, with more room to explore the tools.
The homepage, SmoothyApp page and Multicam page include the updated owner notice, Discord/social links, source-clip and nested-sequence guidance, and the reminder to review both speakers and audio sync. Multicam’s 1.5.1 duplicate-timeline workflow is being tested, with the latest development fix preserving linked microphone audio and effects on camera clips.
Track licenses in the current music archive remain unverified. Check the track in YouTube Studio before publishing, including its attribution requirements.
1.5.1 is still in development. Public desktop downloads remain 1.5.0.
Release update — October 4: Mac 1.5.1 is now available, signed and notarized. Windows remains on 1.5.0 while its update is being built. See the 1.5.1 release notes.
Improved
A smaller Multicam notice
The Multicam warning on the homepage, SmoothyApp page and Multicam page is now a compact, softer notice. Open Details to read the full update, support links and timeline review guidance.
The close button still remembers dismissal across pages and reloads.
Improved
Totals tucked under the navbar
The install and revenue totals now hang from the navbar’s bottom-left instead of sitting on top of it, with a softer lime tint so the tab reads as part of the navigation on desktop and mobile.
Improved
Totals attached to the navbar
Moved the install and revenue totals into a small tab attached to the bottom-right of the navbar, on desktop and mobile.
New
Install and revenue totals below the navigation
A compact strip was added below the navigation for aggregate installation and revenue totals, including on mobile.
This strip and its public stats endpoint were removed on October 5, 2026. Analytics remain available privately in Admin.
Improved
Less space above the page introduction
Removed the large gap between the Multicam update and the page introduction on SmoothyApp, Multicam and the homepage, on both desktop and mobile.
v1.5.1 New
Coming in 1.5.1: Stock Footage & Audio Library
Your next shot and soundtrack belong close to your edit. The new Stock Footage & Audio Library page previews two free tools coming in SmoothyApp 1.5.1.
Stock Footage: search Pixabay, Wikimedia Commons, Internet Archive and NASA together, preview clips in the app, save an MP4 and send it to Premiere’s Project panel.
Audio Library: browse an unofficial YouTube Audio Library archive, preview artist-made music, star your favorites and start with music curated by the team in Staff picks.
One workspace: discover media alongside your editing tools, then place imported files on your timeline. Source links and license details help you check each item’s terms.
The current music archive does not supply verified track licenses. Check the track in YouTube Studio before publishing, including whether attribution is required.
1.5.1 is still in development. Public desktop downloads remain 1.5.0; this is a preview of the upcoming release.
Release update — October 4: Mac 1.5.1 is now available, signed and notarized. Windows remains on 1.5.0 while its update is being built. See the 1.5.1 release notes.
New
Audio Library curation
Admins can search the audio archive, review aggregate favorites, and choose Staff picks.
The service counts one active favorite per track and anonymous app installation, including
free users, and removes its contribution when a track is unstarred.
The desktop interface is being tested in the local 1.5.1 build. Public desktop downloads
remain 1.5.0; community favorites start arriving as users receive a compatible build.
The privacy policy now describes anonymous favorite sharing and local-only favorites.
Improved
Multicam update notice
Multicam wasn’t working correctly in the previous update, 1.5.0. I’m sorry about that.
A fix is being tested for 1.5.1, including source clips and nested sequences.
Public desktop downloads are still 1.5.0.
The homepage, SmoothyApp page and Multicam page now show a dismissible update notice.
Close it once and it stays hidden on future visits in the same browser.
We’ve added a shared Pixabay search service for the next SmoothyApp release. Official app builds will include Pixabay in Stock Footage and All sources without asking you to create an account or supply an API key.
The service keeps credentials on the server, caches search results and limits requests. Clips retain their source links and usage terms. The current public desktop release remains 1.5.0.
v1.5.0 New Improved Fixed
SmoothyApp 1.5: SVG importer, editable captions and a new workspace
SmoothyApp 1.5 is available for Apple Silicon Macs and Windows x64. The Mac build is signed and notarized. Download for Mac or Windows. Restart Premiere and reopen the SmoothyEdit panel after upgrading; sign in again to use Studio with the updated secure connection.
New
SVG importer & Assets: convert SVGs and images into PNGs, preserve transparency, set a proportional output size, paste from the clipboard, export multiple files, or send the selected PNG to Premiere.
Edit caption text and cue timing. Find and replace across the transcript, with case and whole-word options and one-step undo.
A collapsible sidebar that remembers its state, with colored tool navigation and simpler account and connection controls.
Shorts sources for Premiere sequences, transcripts, audio/video files and YouTube transcripts, with Multiple shorts and Best part modes.
Improved
SVG imports default to 1000px wide with proportional height, including batch exports. You can still choose a custom width.
Direct caption controls for language, model, engine, line length, line count and duration, plus local reformatting.
Shorts history search, separate title and description copying, cancellation and a history-save retry.
Camera mappings persist, and each tool explains what its action does above the buttons.
Refreshed homepage and plugin page, interactive 1.5 mockups, a dedicated Assets page, and new 1.5 guides.
The Assets preview and sharing images use the Smoothy cup logo as the sample SVG.
The Assets page and SVG guide explain the Illustrator/converter detour and how to paste copied images with Ctrl+V or Cmd+V before sending them to Premiere. Removed the Assets item from desktop and mobile top navigation and the New badge from its footer link.
Clearer search titles, social previews, article metadata and links between feature pages and guides.
Fixed
Signed Studio sessions and scoped relay tokens replace caller-supplied user IDs. Premiere bridge connections are local and authenticated, and downloaded Whisper engine archives are verified.
Mac automatic updates include the ZIP payload alongside the DMG installer.
Centered the Studio Shorts sign-in panel, including its heading, feature list, button and credit note. Small windows keep the panel scrollable.
Settings keeps its title and close button below the Mac window controls while the options scroll separately. The first row stays visible when scrolling back to the top, and reopening Settings starts at the top.
Improved source and sequence timing, selected microphone handling and mixed-frame-rate processing.
Clearer per-file asset errors and proportional sizing during export.
New multicam and default silence-removal sequences do not copy existing effects and titles. Shorts analysis provides ideas and markers for review rather than a finished vertical edit.
Improved
Usage opens first in admin
Improved
Usage first. Usage is now the first admin tab and opens automatically when you visit the admin panel.
New Fixed
Assets activity in admin usage
New
Admin Usage has an Assets activity summary for successful PNG exports (including Save As), sends to Premiere and total actions. Each successful image counts once per action, and Assets appears as one tool in the ranking.
Tracking is prepared in the desktop source for the next app update. Published 1.5 does not report Assets actions, so historical usage cannot be recovered. Events use the existing anonymous install ID and action names.
Fixed
The Tool runs total now counts tool events instead of including launches and heartbeat pings.
Improved Fixed
Clearer editing guides and website navigation
Browse editing guides by task, with an on-page contents list and related articles.
Corrected older guides to match the current desktop app and web dashboard, including local processing, Premiere sequence limits and the manual Resolve subtitle workflow.
Removed missing image references and repaired links to retired product pages. Older moved URLs now redirect to the relevant current guide or product page.
Improved search metadata, article information, canonical URLs and sitemap dates. Added an article feed.
Account and app screens stay out of search results; public product pages and guides remain crawlable.
Fixed
Shorts analysis compatibility fix
Fixed
Fixed Shorts analysis failing with “Reasoning is mandatory for this endpoint and cannot be disabled.” Studio now allows the AI endpoint’s default reasoning behavior while returning the final result.
Improved
SmoothyApp 1.5 availability on Mac and Windows
Improved
The SmoothyApp download announcement now clearly confirms 1.5 availability on both Mac and Windows, with a link to explore the new features.
Improved
Free tools, no account needed
Improved
Added “Free forever. No account needed.” to the home and plugin page introductions, with “No sign-up. No credit card. No trial.” beside the downloads.
Removed the version number from the SmoothyApp page heading and title. Release notes still identify the app version.
Studio AI remains clearly optional.
v1.4.0 New Improved
Captions in 99 languages
New
Language picker. Choose Auto-detect, or pin the exact language from every one of the 99 languages Whisper supports (English, Spanish, French, German, Japanese, Chinese, Arabic, Hindi, and so on). Auto-detect figures out the spoken language for you.
Multilingual models. The model list now includes Tiny, Base, Small and Medium in both their English-only and multilingual variants, alongside Large v3 Turbo. Pick a multilingual model to transcribe anything other than English.
Improved
Clear guard rail. If a language is paired with an English-only (.en) model, the app says so and tells you to switch to a multilingual model instead of quietly producing English text.
Better progress text. While transcribing, the status line names the language (or says it is detecting one) and the engine in use.
v1.4.0 New Improved
More languages and a signed Mac download
New
Multilingual captions. Choose a spoken language or let Smoothy detect it with a multilingual Whisper model. The available choices include many languages outside Premiere Pro’s built-in Speech to Text list.
Signed Mac installer. The macOS 1.4 download is signed with Developer ID and notarized by Apple.
Improved
The SmoothyApp preview now shows the 1.4 Captions settings, including model, language, and engine controls.
The free DaVinci Resolve subtitle guide now has its own section with a simple SRT timeline preview.
Improved
A clearer free subtitle workflow for DaVinci Resolve
The SmoothyApp page now walks through the free DaVinci Resolve subtitle workflow in three visual steps: generate captions in SmoothyEdit, save the SRT, and import it as a subtitle track in Resolve. The plugin availability note now appears at the bottom of the page.
Improved
A clearer SmoothyApp page
Improved
Added icons to the desktop app features and a simple timeline preview for the Resolve subtitle workflow.
Moved the active development note into the page content and simplified the DaVinci Resolve coming-soon message.
Removed outdated Mac installation advice, the older compatibility notice, and Resolve email signup forms.
Improved
SmoothyApp page: mockup beside the copy
Improved
Two-column hero. The app mockup now sits on the left with the headline, description and download buttons on the right, so the first screen shows the product instead of a centered block of text.
Clearer status notes. The “active development” and DaVinci Resolve notices were rewritten to be shorter and more direct.
Proper download icons. The macOS button now carries the Apple mark alongside the existing Windows logo.
New Improved
New auto-multicam page + a full free-tools guide
New
Auto-multicam landing page./features/auto-multicam now explains how speaker-based camera switching works, who it’s for, and why it’s free — with a side-by-side comparison against paid auto-multicam plugins and doing it by hand.
The SmoothyApp and auto-multicam pages now answer questions in structured FAQ markup, so search engines and AI assistants can read the answers directly.
Sitemap updated to include the app and auto-multicam pages.
Improved
Clearer pricing: free app, optional Studio
Improved
Honest positioning everywhere. The homepage, page titles, footer and FAQs now say “free and open source app, optional Studio cloud AI” instead of implying the whole product is free.
Rewritten pricing page. Two products instead of a confusing Free/Premium split: the App is $0 forever (multicam, silence removal, captions, compressor — MIT, no account), and Studio is the optional cloud add-on, free to start with a $10/month Pro plan.
No more fixed “16 tools” claim. Studio is described as a cloud add-on that grows, so adding the next cloud tool won’t make the FAQ wrong.
Best Shorts is clearly labelled. It’s marked “Studio” on the app page and in the desktop sidebar instead of being listed among the free local tools.
Studio naming unified. The dashboard, account pages and desktop app now call the paid tier “Studio” rather than “Premium”/“Studio Pro”.
The desktop app keeps its local tools free and badged-free; paid cloud tools live under a single Studio group in the sidebar.
v1.3.3 New Improved Fixed
Reliable captions, a real update flow, and a focus on the core app
A big quality pass on captions and updates.
New
Transcribe any audio or video file. The Captions tab now has a source switch, so you can generate subtitles from a plain file on your computer — no Premiere sequence required. Handy if you just want an SRT to import into DaVinci Resolve.
Cancel a transcription mid-run. A Cancel button now appears while captions are generating, so a long file no longer means waiting it out.
A proper update panel. Updates now show up in Settings with the full “what’s new” notes and a Restart & Update button, so you can see what a version fixes or adds before installing.
Join our Discord from the app’s sidebar and Settings.
Improved
Update checks are more reliable. Fixed cases where the update button stayed disabled or hidden after a download, and where clicking it could fire twice.
Fixed
Captions no longer stop partway through a long recording. A timestamp glitch could make the subtitle timings collapse after a few minutes, so players and Premiere appeared to cut the file off. Timings are now guaranteed to be valid and in order.
“Send to Premiere” no longer throws os is not defined.
A note on DaVinci Resolve and UXP
The DaVinci Resolve bridge and the Premiere UXP extension have been removed for now so we can focus on making the core app rock solid. They’ll return as soon as they’re ready.
Using DaVinci Resolve Free? You can still make subtitles today — see the free guide.
v1.3.7 Fixed
Fixed: update bar button + stuck-update warning
Fixed
The update bar’s “Restart to Update” button now works. It previously had no click handler at all — clicking it did nothing, which looked exactly like being stuck in an update loop: the app kept telling you an update was ready (and after every restart it re-offered the same update) because the install was never actually triggered. The button now installs the update and relaunches into the new version.
Stuck-update detection. If a downloaded update never installed (the running version is still older than the downloaded one), Smoothy now tells you explicitly in the update bar and Settings, and skips re-downloading the same update so the loop can’t repeat.
v1.3.5 Fixed
Fixed: captions failing with a missing-file error
A quick fix for anyone hitting the error below while generating captions.
Fixed
Captions no longer fail with “ENOENT: no such file or directory … smoothyedit-whisper-…json”. The transcription output file was being deleted a moment before the app read it, so generation aborted at the very end. The app now reads the result before cleaning up, and captions are produced as expected.
v1.3.4 New Improved Fixed
Real GPU transcription, a model picker, and caption cleanup tools
This release rebuilds the transcription engine so captions actually use your GPU.
New
Real GPU acceleration. Transcription now runs the whisper.cpp engine with a proper CUDA build (the CUDA runtime is bundled), so NVIDIA cards are used instead of quietly falling back to CPU. Apple Silicon uses Metal. Caption Settings shows which backend you’re on — for example “Running on GPU (CUDA)”.
Pick your transcription model. Choose Tiny, Base, Small, Medium, or Large v3 Turbo in Caption Settings. The model downloads on first use and your choice is remembered for next time.
Caption cleanup tools. “Capitalize All” and “Remove Punctuation” apply to every generated caption and rebuild the SRT/VTT instantly.
Improved
Clearer progress. The app now tells you when it’s downloading the engine and shows exactly where it’s running, for example “Transcribing on CUDA…”.
Fixed
GPU builds that silently fell back to CPU. The previous native binding targeted the wrong CUDA architecture and omitted the CUDA runtime; the engine is now downloaded and run directly.
Transcription engine switch. Settings → Captions now has an engine picker: Auto (default, uses the GPU when available), GPU (CUDA), or CPU (all cores). The CPU engine uses every thread your machine has, so it’s as fast as CPU can get.
Fixed
Automatic GPU → CPU fallback. If the CUDA engine crashes or can’t start at runtime (driver problems, unsupported cards, VRAM exhaustion), Smoothy now retries once on CPU instead of failing the transcription.
“Send to Premiere” no longer imports partial captions. Importing now uses Premiere’s dedicated caption-track API instead of generic clip insertion, so the full set of cues lands on the sequence every time. If Premiere still refuses, you get a clear message with the cue count.
Sequence audio is now trimmed correctly. Sequences with trimmed clips transcribed from the wrong part of each source file (the clip’s in/out points weren’t reported). The stitched audio now matches the timeline exactly.
More resilient Windows updater. Updates install and relaunch with isForceRunAfter, so a completed update can no longer leave you restarting on the old version.
v1.3.9 New Improved Fixed
macOS build: GPU captions, engine switch, and update fixes
New
SmoothyEdit for macOS. The desktop app is now built and published for Apple silicon (arm64), matching the Windows feature set. Download it from the site; existing installs auto-update.
Improved
Transcription engine switch (Settings → Captions): Auto (GPU if available), GPU (CUDA), or CPU (all cores). If the GPU engine fails or is slow, switch to CPU — Auto retries on CPU automatically.
whisper.cpp CLI engine with real GPU acceleration and a model picker, so captions run locally and faster.
Fixed
Reliable caption import into Premiere via createCaptionTrack (CEP host script v7) instead of flaky clip insertion.
The update bar’s “Restart to Update” button now installs the update and relaunches, and the app warns you when a downloaded update failed to install instead of looping.
v1.3.2 Fixed Improved
Full-length captions, GPU acceleration, and a working Send to Premiere
Captions got a big reliability pass on Windows. Here’s what changed.
Fixed
Captions cover the entire sequence. Transcription previously read only the first clip on each audio track, so a one-hour podcast could come back as a 14-minute transcript. Audio is now built from every clip on the tracks you select, honoring each clip’s in/out points and its position on the timeline.
Send to Premiere no longer fails with a “header error.” The caption file is now written by the desktop app (the same bytes as Save SRT) and handed to Premiere for import, instead of being rebuilt inside Premiere’s scripting engine with a broken Windows path.
Audio track selection works. The track checkboxes in the Captions panel now control which tracks are transcribed.
Improved
GPU acceleration is automatic. Transcription picks the best backend for your machine — CUDA on NVIDIA, Vulkan on AMD/Intel, and Metal on Apple Silicon — and falls back to multithreaded CPU only if no GPU is available. Expect a large speedup on start-to-finish time.
The app now reports the detected backend and the extracted audio length in its logs, so a short transcript is never silent again.