what's new in sync.: product updates and fixes

Updated November 1, 2026 with additional October improvements and fixes.

• An interactive editor inside ChatGPT - Browse your sync. labs projects, upload or select media, choose a model, and create videos without leaving the conversation. Review the result in the player and compare it with the original input.
• Translate and dub videos in ChatGPT - Choose Translate & Dub, select your video, and search for the source and target languages. Review the dubbed result, download it, or reuse the video for another language.
• See the estimated cost before generating - ChatGPT now shows the expected cost in credits or dollars before you submit. Translate & Dub estimates include both dubbing and lip sync, with any external-provider charges shown separately as excluded from the estimate.
• More natural dialogue edits - Edit Dialogue uses the surrounding sentence to shape replacement speech and fills gaps with room tone matched to the source when suitable audio is available. Replacement words also land closer to their original timing.
• Leave selected footage untouched while dubbing - In Advanced Studio, mark clips or timeline ranges as No lipsync to keep their original video while translated audio continues. Turn lip sync back on for a range whenever you need it.
• Choose regional dubbing dialects - Studio now offers regional language choices, including Spanish for Argentina, Chile, Spain, and Mexico. The timeline uses the same searchable language picker as the other dubbing flows.

Improvements

• Return to recently visited projects and Home with their existing content visible while data refreshes. Studio keeps timeline thumbnails and waveforms when you return to the same project.
• Choose a desktop Studio model with the arrow keys and adjust its settings with the keyboard.
• Billing keeps the previous rows and totals visible, marked as loading, while you change periods or filters.
• Removing a team member now revokes their API keys in that team. The confirmation explains which integrations may stop working.
• Add a pronunciation hint in Edit Dialogue to guide how a replacement word should sound.
• Edit Dialogue warns while you type when replacement wording may be too long to fit, and explains when a preview exceeds the 100-edit limit.
• Videos without an audio track now open the voiceover flow from Edit Dialogue. Videos with no detected speech offer an explicit Add a voiceover action.
• Edit Dialogue now uses sync-3 for lip sync, including drafts reopened from older-model results.
• Dubbing estimates now appear beside the translation controls in Studio Lite, Advanced Studio, and Assistant, with lip sync priced separately.
• Studio resizes oversized JPEG and PNG photo uploads to fit image-to-video limits while preserving orientation and aspect ratio.
• Uploading an identical file again can now reuse your existing saved asset instead of transferring the bytes a second time.
• Scale plan API users can submit batch rows directly as JSON, without preparing a JSONL file.
• Voice cloning now waits and retries when shared cloning capacity is temporarily busy. You can stop waiting without losing your name or samples.
• Asset source selection now supports arrow-key navigation, and preview volume controls stay visible when reached with the keyboard.
• Studio history now includes work from connected clients such as ChatGPT, Claude, Gemini, and MCP, along with API-key generations in their owner’s private project. The API can also return generation history for a selected project.
• Team members can rename and revoke their own API keys, and give new keys an optional name during creation.
• When Safari or another browser cannot decode audio for a partial sync, Studio offers Replace audio while keeping your video, settings, and speaker selection.
• Completed Studio results now offer Download original when the browser cannot play their video format.
• Mark in shows its applied marker immediately above the timeline playhead, without waiting for hover.
• Duration-limit messages now explain when a rounded display hides the extra time that put a file over the limit.
• Studio side panels open and close with smoother transitions.
• Studio asks before discarding an unfinished custom voice. Cancel the prompt to keep your voice name and samples.
• Team admins can resend pending invitations without cancelling and recreating them.
• API users and agents can check their account, workspace, plan limits, and available allowance in one request with GET /v2/account.
• API billing and limit errors include recovery details such as available credits, required plans, and billing links. Rate-limit responses include retry timing.
• The ChatGPT guide now covers workflow selection, uploads, project history, estimates, and recovery.
• The MCP setup guide explains how to connect your own agent, with instructions for Claude, Codex, Cursor, and other supported clients.
• The dubbing language picker fits more choices on screen, with search beside the heading.
• Failed and cancelled uploads now show their status in the uploads widget.
• Create and rename API keys in dedicated dialogs, with newest keys first and a clearer table. Closing the secret dialog or cancelling a revocation returns focus to its original control.
• Onboarding makes the free option clearer, lets you revisit answers, and offers a way to skip the optional referral question.
• Studio explains remaining free videos, watermarking, and plan requirements more clearly before generation.
• Media previews show upload progress, and input controls explain unsupported files and why generation is unavailable.
• Studio Lite asks for confirmation when attached audio appears silent before you spend a video.
• Result downloads give immediate feedback, prevent accidental repeat clicks, and offer Download again when needed.

Bug fixes

• Studio timelines can now render clips that mix audio sample rates or mono and stereo tracks.
• Voice samples extracted from high-bitrate video are compressed to fit the cloning service’s size limit.
• Fixed uploads failing when another team member opens a shared plugin project.
• Studio media pauses when you leave the page and stays paused when you return. Returning from Home also keeps recorded takes and voice samples available.
• Studio repairs overlapping audio clips when they can be separated without losing audio. If the repair would push audio past the video, Studio keeps the layout and explains what to fix.
• Fixed later clips losing their audio when No lipsync preparation removes gaps between video clips.
• Studio can submit generations when browser storage or Web Locks are unavailable. A notice explains when recovery will not survive a reload.
• Audio recordings that reach their time limit are now kept and applied instead of disappearing.
• Temporary errors on shared-result links now offer Try again instead of Content Not Found.
• While editing a draft from a completed lip sync result, the Studio header Download button downloads that result.
• Failed API-key revocations and integration removals now keep their confirmation open so you can retry or cancel.
• Reloaded H.264 MOV inputs can start native playback without waiting for the server to identify their codec, when the browser supports the stream.
• Fixed duplicate generation failure notifications. The selected failed result now shows one detailed error with its recovery action.
• Fixed voice names being accepted in Studio and rejected after sample upload. Invalid names now show an inline error before uploading, with your name and samples retained for correction.
• Fixed translated audio from a previous video remaining selected after changing the source video.
• Fixed deleted frames briefly reappearing at timeline trim boundaries.
• Connecting an already connected integration now returns 409 Conflict and preserves the existing key. Disconnecting an integration that is not connected returns 404 Not Found.
• Rejected OAuth refresh tokens now return invalid_grant so clients can recognize when fresh authorization is required.
• Projects and generation history keep loading while more items remain visible, without requiring you to scroll away and back.
• Renaming an API key trims surrounding spaces and uses a default name when the new name is empty.
• Deleting a custom voice hosted by sync. labs no longer fails on temporary provider delays. Voices on your own connected provider account keep their existing deletion behavior.
• Fixed duplicate lifecycle emails after temporary delivery interruptions.
• Projects with existing apostrophes or commas in their names can be updated without renaming them.
• Creating a team keeps your details and stops with an explanation if its logo upload or workspace switch fails.
• Studio shortcuts no longer act on the timeline behind open dialogs or menus. Escape closes confirmation dialogs without triggering unrelated timeline actions.
• Failed generation deletions remain available to retry. Deleting the final generation opens an empty draft instead of leaving the deleted result on screen.
• Sharing an already published result no longer republishes it or repeats the public-link warning.
• Support chat continues checking for unread replies while the page is visible.
• Team role changes show the pending selection and prevent overlapping updates. Demoting yourself to member removes admin controls immediately.
• Previously accepted invitation links still offer a way back to your team after their original expiry date.
• Asset rename and delete errors explain permission refusals instead of asking you to retry an action you cannot perform.
• Recording shows a Microphone unavailable message when another application holds the microphone.
• Billing navigation moves to the actual adjacent billing period without date drift.
• The DaVinci Resolve download page lets you restart the installer download for your operating system.
• Account-deletion confirmation accepts surrounding email whitespace and supports Enter.
• Login keeps email and verification-code errors visible, including guidance for rejected or expired codes.
• Mobile Studio keeps rendering status readable and opens history menus reliably when tapped.
• Result ratings sit beneath the video instead of covering it, and narrow audio previews keep timing labels clear of the waveform.
• Project searches treat percent signs and underscores literally.
• The downloadable API specification lists public operations and the production server, without internal endpoints or a localhost address.

• Know how long your generation should take - Studio now shows an estimated time remaining in the player and history. If a generation takes longer than expected, you’ll see delay guidance and a direct way to contact support.
• Keep creating after you close the tab - Start a video with text-to-speech in Studio Lite and leave the rest to sync. labs. Once accepted, speech creation and video generation continue without keeping the tab open. Studio also recovers accepted speech jobs after a reload instead of creating the same audio again.
• Download API results again, without regenerating - Request a download URL for a completed generation using its ID and your API key. No Studio project is required. Retrieve the existing output while it’s available, without paying for another generation. Explore the API

Improvements

• Correct a speaker selection by dragging or resizing its box, or place a box yourself when detection misses the face.
• Studio result previews and signup onboarding load with less unnecessary work.
• Saved video posters now match the current output and plan, so finished results can appear before the video loads.
• Connected ElevenLabs accounts now load the full available voice library, including workspace-shared voices. Restricted voices show why they cannot be used.
• Disabled Sync and speech Preview controls now explain what’s missing and offer retry guidance when eligibility checks fail.
• API keys can create and check transcription jobs and dialogue-edit previews.
• Sign-in codes now appear first in email subjects and previews, making them easier to find without opening the message.
• Plan comparison cards make watermark availability clearer while preserving your plan’s prices and limits.
• The profile menu now works as a named button for keyboard and screen-reader users.

Bug fixes

• Fixed scheduled Studio Lite generations staying stuck after their input uploads finished.
• Fixed repeated Studio submission actions creating duplicate generations.
• Projects with pending or processing generations can no longer be deleted while that work is active.
• Fixed completed assistant uploads being lost after moving to audio input or reloading, and late uploads changing a different session.
• Restored right-click actions on finished assets in desktop list view.
• Fixed restored drafts showing the wrong upload preview or selecting a model that is no longer available.
• Fixed delayed video analysis being applied to a different draft or input.
• Fixed video-only timeline trims failing when the browser had no audio encoder.
• Fixed the space bar losing control of playback after a timeline generation completed.
• Fixed trim-to-limit outputs being rejected because encoding pushed them slightly over the duration limit.
• Fixed voice cloning proceeding with missing samples after an upload failed. Your name and samples now stay in place for retry.
• Fixed cut-off generation estimates and credit reservations using the full audio length instead of the duration being processed.
• Fixed usage totals not refreshing after generation or speech completion, and aligned credit adjustments across activity, history, and CSV exports.
• Fixed top-up dialogs rounding away cents and fallback plan cards showing the wrong voice-clone limit.
• Fixed pasted sign-in codes with spaces or hyphens losing digits.
• Fixed the preview keeping a watermarked result after an eligible plan upgrade, even when a clean output was available.
• Fixed timeline cost estimates changing incorrectly when audio was trimmed or split into clips.
• Fixed voice cloning through API keys failing because the request was not assigned to its owner.

• Choose one audio source. Non-segmented lipsync requests require exactly one audio OR text input. Requests with both, or with multiple text inputs, return HTTP 400 instead of silently ignoring extra inputs. Select one source, or use segments with unique refId values for multiple audio/text inputs. Existing requests with one audio or text source need no change.

Improvements

• The Create Generation API reference and error guide explain input requirements and how to correct invalid media.
• Dubbing keeps its existing contract: send one video with dubParams and no audio/text input. Conflicting inputs still return HTTP 422 with generation_input_dub_audio_conflict.

Bug fixes

• Fixed missing media duration reaching video-generation pricing and causing misleading billing errors. Media whose duration cannot be resolved to a finite positive value now returns a coded HTTP 422.
• If you get that 422, check that the source URL returns readable media and that segment or crop windows have a positive duration.
• Temporary media-probe failures return retryable HTTP 503 errors, so integrations can distinguish a source outage from invalid media.

• Start from the outcome you want - The workflow dashboard is now available to everyone. Choose lip sync, translate and dub, image to video, sync. assistant, or the timeline editor, and sync. labs opens the right tools for the job. Projects created in Adobe Premiere Pro and DaVinci Resolve now open in the same guided lip sync workflow when viewed in the App.
• Built-in dubbing now supports 92 languages - Create translated dubs across the App, API, Adobe Premiere Pro, and DaVinci Resolve. The upgraded dubbing engine automatically detects speakers and returns lossless audio for the final dub. Read the dubbing guide
• Studio remembers your model choices - New drafts use the latest compatible model from your project. When you choose a model explicitly, Studio uses it as the starting point for future projects.

Improvements

• Project cards now show when a lipsync is in progress and surface newly added draft media ahead of older results.
• Workflow guidance stays visible as soon as you submit instead of briefly flashing the edit state.
• Asset hover previews now include seek thumbnails, making it easier to scan longer videos.
• Downloading every result in a project is more reliable, with automatic retries and resumable downloads for interrupted transfers.
• Download actions now live in one consistent menu for the current result, every ready result, and watermark-free upgrades.
• Credit activity, plan limits, and auto top-up settings are clearer and easier to manage from billing.
• Duration limits for longer media are now shown in hours, minutes, and seconds.
• Video playback now recovers when a new source is loaded after an error and gives clearer retry guidance.
• Failed generations now show an actionable error with the relevant billing, integration, documentation, or support next step.
• Model and speaker recommendations appear in sequence instead of competing for attention.
• The space bar now controls play and pause across Studio without requiring a click on the player first.
• Studio Lite and shared players now show the current timestamp and total duration.

Bug fixes

• Fixed audio and video recording stopping immediately after it started.
• Fixed generation thumbnails getting stuck in a loading state in Studio and the projects view.
• Fixed workflow results not scrolling correctly on mobile and the video player shrinking to an unusable size.
• Fixed completed uploads remaining in the uploads widget after navigating between projects.
• Fixed dubbing controls becoming unusable when the selected source was muted or silent.
• Fixed browser back and forward navigation leaving Studio on a stale project.
• Fixed model recommendations overriding selected models and generation settings.
• Removed a duplicate download button from the advanced Studio controls.
• Fixed multi-file video and audio drops on the timeline being rejected with an incorrect file-format error.
• Fixed multi-segment timeline generations failing at segment boundaries.
• Fixed the asset picker opening empty and Clear filters leaving active asset filters behind.
• Fixed invited teammates being sent through signup onboarding instead of landing in the team they joined.
• Fixed returning paid users with existing work getting trapped in the signup onboarding loop.
• Fixed usage pages losing every total when one usage source was temporarily unavailable.
• Fixed the Studio assets panel showing assets from other projects when opened from the current project.
• Fixed video analysis enabling occlusion handling without approval.
• Fixed dubbing jobs transiently failing while their finished lossless audio was still becoming available.
• Fixed overlapping controls appearing when starting a new generation immediately after adding audio.

• Image-to-video with sync-3 - Turn a still image into a naturally speaking video. Upload a JPEG, PNG, or WebP image, add audio, choose the face you want to animate, and let sync-3 build the performance. Available in the App, API, Adobe Premiere Pro, and DaVinci Resolve.
• DaVinci Resolve plugin - Bring sync. labs into DaVinci Resolve. Use footage from your timeline or media pool, generate a result, and send it straight back to your project. Download the plugin
• More control on the Timeline - Crop individual clips, undo and redo edits, trim with frame-level precision, and keep full-resolution output through the edit. The preview now matches the final render more closely, so you can make decisions before spending a generation.
• The full creation stack, now in the API - Upload and reuse assets, synthesize speech, clone and manage voices, organize work into projects, generate lipsync, and wait for results in one request. Explore the API
• Create directly in ChatGPT - Upload a video or image, create speech, clone a voice, animate an image, generate lipsync, organize projects, and retrieve results without leaving the chat. Use sync. labs in ChatGPT

Improvements

• Download every completed generation in a project as one ZIP, including work created across the App and API.
• Preview an asset by hovering over it and pressing Space.
• The App now warns before generation when multiple speakers are detected and no speaker has been selected.
• Closed-lip footage now prompts you to use sync-3, which handles that starting position more naturally.
• Compare original and dubbed audio inside the dubbing preview before generating the final video.
• The App reads professional media metadata more reliably for MOV, ProRes, MXF, and DNxHD files.
• Adobe Premiere Pro and DaVinci Resolve can submit another generation while earlier uploads continue in the background.
• Generation errors now distinguish invalid requests, duplicate submissions, timeouts, unavailable services, and concurrency limits, with clearer guidance on what to do next.

Bug fixes

• Fixed sync-3 rejecting some videos that were within the duration limit after sync mode was applied.
• Fixed generated text-to-speech audio not appearing in the preview.
• Fixed the App occasionally staying on the Source view after a generation finished.
• Fixed the Timeline going empty while a generation was processing.
• Fixed audio clips being placed beyond the end of the video track.
• Fixed intermittent Adobe Premiere Pro plugin failures during project scanning, uploads, and authentication.

• Dubbing - Translate any video into another language and lipsync it in one step. Pick a target language and sync. handles translation, voice cloning, and lipsync - 29 languages supported. Available in Studio and via API. Try it in Studio · Use the API
• Assistant mode - A whole new way to lipsync your videos. Drop a video, describe what you want, and sync. handles the rest. No settings to configure, no modes to pick. The assistant recommends the right model, detects speakers, and generates your sync automatically.
• MCP server - Generate lipsynced videos, manage assets, and track renders directly from your code editor or AI assistant. Works with Claude, ChatGPT, Cursor, Windsurf, Codex, and any MCP-compatible client. Get started here.
• sync-3 - Our newest model is now available to all users, including free tier. sync-3 delivers the highest quality lipsync we’ve ever shipped.

Improvements

• Simplified model picker - fewer choices, clearer recommendations.
• Faster speaker detection on uploaded videos.
• App remembers your last visited page (Studio or Assistant) across sessions.
• Plugin now available to all users - no more feature flag gating.
• Headless audio extraction in the Premiere Pro plugin - no more Media Encoder UI popup.
• Audio input is now preserved when replacing video in Lite mode.
• Sync mode selector tooltip now shows the currently selected mode on hover.
• Studio loads faster across the app.
• Unified API-first architecture - Studio, the plugin, and the public API now run on the same foundation, so what ships in one ships everywhere.

Bug fixes

• Fixed speaker selection popover being unclickable and dismissing inconsistently.
• Fixed multi-face prompt reappearing after being dismissed.
• Fixed webcam recording starting with a black frame instead of a live preview.
• Fixed .qt video uploads behaving inconsistently in Studio.
• Fixed downloads forcing .mp4/.mp3 filenames instead of preserving the original extension.
• Fixed share page video player missing its thumbnail poster.
• Fixed audio assets opening in a new tab instead of downloading.
• Fixed billing tab not showing all requests on longer billing periods.
• Fixed video URL submission firing before the upload finished.
• Fixed react-1 API usage not appearing in the billing dashboard.
• Fixed “Add member to team” failing.

• Adobe Premiere Pro plugin - Lipsync without leaving your timeline. Select in/out points on your sequence, pick clips from the media browser, or upload directly into the plugin. Generate, preview, and drop the result back into your edit. Built for the way editors actually work. Get the Premiere Pro plugin.
• Sync mode selector - When your audio and video have different durations, you can now choose how the model handles the mismatch. bounce loops the shorter media back and forth, cut_off trims the excess, silence pads the gap, and remap stretches to fit. Learn how each mode works
• API-first architecture - Revamped our backend to be API-first - the same endpoints that power Studio are now available to you. First up: the Assets API lets you list, search, and filter your media library programmatically. You can also pass an assetId directly to the generation endpoint instead of a URL. More endpoints coming soon.
• CSV usage export - Download your detailed spending breakdown for any date range from Usage for reporting or feed it into other tools.
• lipsync.com - A central resource for everything lipsync - guides, use cases, comparisons, and tools in one place. Check it out

Improvements

• Select multiple assets in a project and delete them in bulk.
• Studio loads faster - preloaded video thumbnails and deferred heavy assets for quicker initial page load.
• Faster API responses - improved authentication speed and optimized generation queries.
• Face selection is now always visible after video upload - when multiple speakers are detected, you’re prompted to pick the active face directly on the video.
• Copy Voice ID button in the TTS voice selector for easier API integration with cloned voices.
• Delete your account directly from Settings - no support ticket needed.

Bug fixes

• Fixed billing and usage filters not applying correctly for certain date ranges and plan types.
• Fixed Studio freezing during video upload causing page unresponsive errors.
• Fixed videos showing black screen as first frame in project view.
• Fixed usage dropdown not filtering correctly.

• react-1 - A new model that lets you control performances in post-production. Upload your footage (filmed or AI-generated), then adjust the acting without reshoots. Select head, face, or lips and fine-tune delivery using the emotion wheel. Learn more about react models.
• Audio tags in TTS - Add tags in square brackets like [excited] or [whisper] when generating text-to-speech to control emotion and delivery. Using at least one tag enables ElevenLabs v3 for more expressive speech.
• Rename generations - Give your results meaningful names so they’re easier to find after downloading. Click “…” on any history thumbnail and select “Rename”. Defaults to project name + generation number.
• Microsoft SSO - You can now sign in with your Microsoft account.

Improvements

• Upload panel now auto-hides when all uploads complete instead of retaining previous state.
• Smart suggestions now appear when generation results aren’t great, with actionable steps to improve them.
• Simplified model picker with settings moved to a separate dropdown in the same location.
• Cloned voices now work over API. Copy Voice ID directly from the voices dropdown in Studio.

Bug fixes

• Fixed assets filter clear button not working.

• Speaker Selection - Manually select speakers directly from your video for targeted lipsync edits. When 2+ speakers are detected on the same frame, the selection button appears automatically. No more guessing who’s speaking - just click, sync, and go.
• Reasoning mode for lipsync-2-pro - New toggle automatically detects and fixes artifacts, occlusions, and extreme poses for cleaner, more stable results. Takes a bit longer to process, but the quality boost is worth it.
• Redesigned assets view - New table layout with sortable columns, thumbnails, and rich metadata. Right-click any asset for quick actions, see who created what in team projects, and find files faster with improved organization.
• Resumable & cancellable uploads - New upload system handles everything from tiny files to multi-GB projects. Pause, resume, or cancel anytime-uploads survive page refreshes, browser restarts, and flaky network conditions. The new upload widget shows accurate progress, speed, and ETA, with navigation guards to prevent accidental data loss.

Improvements

• New upload widget for controlling and monitoring all uploads in one place.
• Uploads now auto-recover from offline states and network transitions.
• Improved pricing clarity for Teams with better billing period explanations.
• New segments icon in timeline mode for better visual clarity.
• Face detection now uses best-in-class model for faster, more accurate speaker detection.
• New Experimental Features toggle in settings to enable all beta features at once.
• Emotion selection is now shown in generation history for past projects.
• Face detection overlays now hide during video playback for cleaner viewing.

Bug fixes

• Fixed generation deletion not working properly.
• Resolved audio-video detaching errors where videos were incorrectly treated as silent.
• Fixed an issue where projects were incorrectly loaded when switching teams.
• Fixed voice clone selector not showing the correct selected voice.
• Fixed extra bottom padding on mobile that was happening in some scenarios.
• Fixed Studio Pro left panel re-rendering issues for smoother performance.

• Blazing fast performance - Completely rebuilt Studio state architecture delivers smoother interactions, faster loading, and a more responsive experience across all features.
• Instant generation delivery - Results and assets now served at the edge for quicker access to your creations.
• Enhanced voice cloning - Updated ElevenLabs integration with latest API requirements for more reliable voice cloning.
• Optimized uploads - Client-side media compression automatically reduces file sizes for faster upload times.

Improvements

• Improved tooltip visibility in model preferences for better clarity
• Easier asset discovery in Lite mode with improved UI
• Better error handling across the app

Bug fixes

• Fixed crash when selecting models in billing usage view
• Resolved issue preventing typing in TTS box in Advanced mode
• Fixed current frame counter showing larger than total frames in player
• Sync modes in Advanced mode now persist when moving audio in timeline
• Fixed scrubbing functionality in preview mode
• Generation thumbnails now correctly show output instead of source video
• Share buttons now work as expected
• Improved error messages for audio duration issues
• Resolved video upload errors
• Fixed bad inputs with zero-length segments from Studio

• Full mobile experience - Everything you can do in Lite mode on desktop is now available on mobile, bringing the complete Studio experience to your phone.
• Settings that persist - Your generation settings now carry over to new projects and drafts, saving time on every creation.
• Rate generations to improve the models - Provide feedback on your generations to help us enhance our lipsyncing models for everyone.

Improvements

• New drafts automatically inherit settings from your last generation
• Smoother visual feedback when detaching audio from videos
• Enhanced asset management with improved sorting and filtering
• Model notification indicator now dismisses automatically after first interaction

Bug fixes

• Projects now correctly sort by most recently used
• Asset filters dropdown opens reliably on all clicks
• Voice clones with identical names no longer cause selection issues
• Billing links now redirect to the correct subscription page
• Cost estimates now accurately reflect your selected sync mode
• Various UI refinements for a smoother experience

• More room for your video - Studio Lite now gives you more space to see your work with cleaner audio input controls for TTS, uploads, and URLs.
• Lipsync on the go - Complete mobile redesign with most features available in a cleaner, touch-optimized interface.
• Assets in Studio Lite - Access and manage your assets directly within Studio Lite for seamless project collaboration.
• Multiple segments support - Generate API now supports syncing different audio/TTS inputs to specific video segments, enabling precise control over multi-part lipsync projects with audio cropping capabilities. Read the segments guide.

Improvements

• TTS script now remembered when editing previous generations
• Improved timeline tracks virtualization with more lightweight implementation, making interactions 60fps smooth
• Faster media parsing in Studio Advanced and Lite, making the experience more seamless
• Improved voice selector UI for better user experience
• Model picker and lipsync button now update correctly when using TTS
• Support chat bubble repositioned to prevent overlap with interface elements
• Updated usage calculation to account for applied credits
• Clicking ‘New Generation’ in Studio Advanced now opens a new draft with the generation’s inputs already filled in
• Improved error toasts and documentation for unsupported media inputs

Bug fixes

• Fixed toggle for switching between source and lipsynced videos within Studio Advanced
• Fixed click interaction in after deleting drafts and generations
• Fixed the generation result not getting updated in Studio Advanced after completion
• Fixed drag-and-drop not working for assets in Studio Lite

• Share with anyone, anywhere - Instantly share your lipsynced videos with friends and colleagues on X, Facebook, LinkedIn, or via email.
• Smart limit notifications - Get a clear UI feedback when approaching generation, concurrency, or free credit limits without losing your work.
• Bigger, better video player - Enjoy a larger, responsive player that adapts to your screen for the best viewing experience.

Improvements

• History panel now opens by default in Studio Pro for faster access
• Redesigned “Add Assets” button floats on the timeline for easier reach
• Full player controls now available in fullscreen mode
• Lipsync model selector now remembers your last choice
• Enhanced history thumbnails with clearer selected state for better visibility

Bug fixes

• Fixed organization creation flow preventing errors when navigating away
• Timeline controls no longer hidden after generating in Studio Pro
• Generation results now update immediately when completed
• Payment failure messages no longer block the video player
• Full-screen mode stays active when switching between views
• Segment markers now visible without hovering

• Studio Lite - a new, simplified way to lipsync your videos. For more creative control, toggle switch to get into Pro mode.
• lipsync-2-pro - our latest studio-grade model with 4K support is now available to all paying users.
• New history - completely revamped History to find past generations easily.
• Draft edits - quickly edit multiple versions and iterate without re-uploading assets.

Improvements

• All new projects default to Studio Lite mode
• Audio state now remembered when switching between upload methods
• Clearer, more helpful error messages throughout the app
• Improved performance of loading custom voices
• Upgrade video player to support all major codecs
• Support messages connect directly to chat instead of email
• Better loading states - no more flashing screens

Bug fixes

• Fixed watermark not disappearing after upgrade
• Resolved video player sizing and playback issues in Safari
• Fixed video recording issues in Firefox and Safari
• Adding assets on mobile now added immediately to timeline
• Fixed deleted videos reappearing after upload
• Fixed keyboard issues for text-to-speech on mobile
• Session expiry redirects to login instead of showing errors
• Various bug fixes and improvements across the board