Editing & Tools

Can Gemini Watch Videos? Yes: YouTube Links, Upload Limits, and a 73s Test (2026)

Fuxuan Guo
24 min read
Can Gemini Watch Videos? Yes: YouTube Links, Upload Limits, and a 73s Test (2026)
Contents
  1. Can Gemini watch videos in Google’s own apps (YouTube links, uploads, and limits)?
  2. How do you let Gemini watch a local video and cut the best part in Antigravity and ChatCut?
  3. What did Gemini get right — and what did it get wrong on our 73-second video?

Yes — if you are asking can Gemini watch videos, Gemini supports video uploads and questions about YouTube content. The exact input limits and available features depend on whether you use Gemini Apps, Chrome, Live, or the Gemini API. Google’s analysis guides describe answering questions about video; they do not establish a local multi-track editing and export workflow. For comparison guides, see Claude and video and ChatGPT and video.

ChatCut is our product. On November 18, 2026, we ran a real test using Gemini 4 Carbon inside Google Antigravity, connected to ChatCut Desktop on macOS. Gemini analyzed a transcript and eight frames sampled every 10 seconds from our 73.5-second loft recording, selected two speech ranges, then cut, captioned, and exported a 16.9-second clip. The original session and tool receipts confirm the workflow; the post-export billing snapshot reports 0.00 ChatCut credits for this project. This tests Gemini working with selected images and a transcript through editing tools, not native video uploads in Gemini Apps or the API. The prompts below are reusable versions of the workflow, not verbatim session messages.

Demo
Selected, cut, and exported by Gemini 4 Carbon in Antigravity + ChatCut Desktop: 16.9 seconds, 1920×1080, 24 fps, H.264/AAC, -18.9 LUFS. Post-export project billing: 0.00 ChatCut credits. Landscape 16:9 framing.

Below are Google’s documented video-input rules, checked on November 18, 2026, followed by our Antigravity + ChatCut test and an audit of what Gemini got right and missed with 10-second frame sampling. For a broader workflow, see can Gemini edit videos or how to edit video with Antigravity.

These five surfaces have different inputs and restrictions. API implementation details and quotas should not be assumed to apply to Gemini Apps.

Google surfaceInputPublished limits or requirementsDocumented use
YouTube in Gemini Apps (Gemini Apps Help)Questions about YouTube videosSigned in; Keep Activity on; unavailable in Live chats and Google MessagesFind videos and ask about their content; this help page does not specify frame sampling
File uploads in Gemini Apps (File help)Supported video attachments2 GB/video, 10 files/prompt subject to availability; 5 minutes total video, or 1 hour on Google AI Pro / UltraAnswers, summaries, and insights
Gemini in Chrome (Chrome Help)Audio/video already played in shared tabsSupported Mac, Windows, or Chromebook Plus; signed in; supported region/language; age requirement varies by countryQuestions about played media when Media understanding is enabled
Gemini Live (Live Help)Camera feed or screen sharingSupported mobile device/account; feature availability variesDiscuss what the camera or screen shows
Gemini API (Developer guide)Uploaded files or public YouTube URLsFiles API: 2 GB free / 20 GB paid; context and request limits also applyProgrammatic video analysis, separate from the consumer app

Google documents finding YouTube videos and asking follow-up questions about their content in Gemini Apps. You can try supplying a public URL to identify the video, but the linked Apps guide does not guarantee that every pasted URL is playable or that every visual detail is inspected. Direct YouTube-URL input is explicitly documented for the API.

Check these distinctions when a YouTube request fails:

  • Keep Activity must be turned on. Google states that YouTube content analysis in Gemini Apps is unavailable whenever Keep Activity is turned off on your Google Account.
  • API rules are separate. Google’s API YouTube guide restricts URL inputs to public videos, with 8 hours/day on the free tier and up to 10 videos/request on Gemini 2.5 or later. These are not documented Gemini Apps quotas.
  • Not supported in Gemini Live or Google Messages. Pasting or asking about YouTube videos is currently disabled inside Live voice chats and Gemini in Google Messages (Gemini Apps Help).
  • Read-only access to YouTube. Gemini Apps cannot display a complete list of your personal watch history, liked videos, saved playlists, or subscriptions, and cannot save videos to playlists or post comments on your behalf.

Ask Gemini to distinguish spoken material from visual observations. YouTube’s Show transcript panel helps check captioned speech and jump to timestamps; inspect the video itself to verify visual claims.

Try this prompt
Watch this public YouTube video and break it into major sections with MM:SS timestamps: [paste YouTube URL]. For each section, list (1) a short verbatim quote from the speaker and (2) what is visibly shown on screen. If a detail comes only from the title, description, or speech without visual confirmation, say so explicitly instead of guessing.

What is the Gemini video upload limit, file size, and format list?

For local files, use Add files → Upload Files in Gemini Apps. Add from Drive requires History on and Google Workspace connected; work/school access also depends on the administrator. Google’s file-upload help and usage-limit help distinguish attachment caps from usage and storage limits:

  1. Attachment size: 2 GB per video, up to 10 supported files per prompt, subject to availability. ZIP attachments cannot contain video or audio.
  2. Combined video duration: 5 minutes normally, or 1 hour with Google AI Pro / Ultra.
  3. Usage and storage: Personal-account compute limits refresh every 5 hours until a weekly ceiling. Chat-history storage is separate from Drive storage; clearing it does not remove duration or compute limits.

The Apps help page does not publish an exhaustive video-format list. The API’s supported MIME types are a separate specification:

  • MP4 (video/mp4) and QuickTime MOV (video/mov)
  • WebM (video/webm) and AVI (video/avi)
  • MPEG / MPG (video/mpeg, video/mpg)
  • Windows Media Video (video/wmv), 3GPP (video/3gpp), and FLV (video/x-flv)

For API models with a 1M context window, Google documents up to 3 hours at low media resolution or 1 hour at high resolution. The same page currently gives inconsistent inline-upload thresholds, so use the Files API for larger videos and check the request-specific documentation.

Use MM:SS timestamps in your prompt so you can return to the claimed moment and check it:

Try this prompt
Analyze the attached video from start to finish. Give me a timestamped table in MM:SS format covering every topic change or shot change, what the speaker says, and any readable text or physical actions on screen. Flag any stretch where audio is unclear or where a visual detail happens too fast to read.

How does Gemini video understanding actually read frames and audio?

Google’s API video documentation describes static and opt-in agentic processing. This does not establish how every consumer-app surface processes video.

  • Static: The documented default is 1 FPS plus audio. Developers can adjust sampling; fast visual changes may be missed.
  • Agentic: Supported models navigate the timeline and load relevant content on demand. Google’s explicit list includes Gemini 4 Carbon, Argon, Hydrogen, 3.8 Flash, 3.6 Flash, and 3.5 Flash Lite; do not generalize that to every “3.5+” model.

Gemini in Chrome has a Media understanding toggle at chrome://settings/ai/gemini for questions about media already played. Gemini Live instead accepts a live camera view or screen share. Neither is the same input path as uploading a saved file to the API.

For this article’s cut, corrected captions, and MP4 export, the editing tool is ChatCut Desktop. A text answer with useful timestamps is an edit plan; it is not yet an edited media file.

How do you let Gemini watch a local video and cut the best part in Antigravity and ChatCut?

For “watch this recording, pick a short highlight, and cut it with subtitles,” connect Antigravity to ChatCut Desktop. Desktop supports macOS 13+ (Apple silicon or Intel) and Windows 10+ x64, not Linux (system requirements). Editing and rendering can run locally; online AI features still require network access, so this is not an offline or no-upload guarantee. Antigravity model access and reasoning usage follow Google’s plans and available models. ChatCut’s credit policy separately covers hosted generation. Uploads, transcription, standard captions, and local export do not themselves consume ChatCut credits. Cloud exports include a free allowance; beyond it, they follow ChatCut’s current credit rules (see Web vs Desktop Export). Local export supports presets up to 4K, and Free access includes core editing. AI image/video generation requires a paid plan and credits. See also editing with ChatGPT.

We created a fresh 1920×1080, 24 fps project and imported the 58.3 MB source recording. The source has a 73.490-second container duration, a 73.168-second H.264 video stream at 23.976 fps, and 48 kHz 24-bit stereo PCM audio. These measurements describe different streams, so they need not end at exactly the same instant. The six steps below cover the connection and the verified editing run, with reusable prompts.

Step 1: Connect Google Antigravity to ChatCut Desktop

In a new Google Antigravity conversation on macOS or Windows, paste the one-line installer prompt from the ChatCut plugin page for Antigravity:

Try this prompt
Read ChatCut.io/antigravity to install ChatCut

The documented installation flow adds the ChatCut plugin, installs and connects Desktop, and asks you to sign in and start a new conversation. Antigravity must be available for your account and region; the supported setup uses the App, CLI, or IDE with the agy CLI on a computer with a graphical desktop.

Step 2: Import the 73-second loft video, transcribe speech, and sample every 10 seconds

Gemini imported the recording, waited for its word-timed transcript, and extracted samples at 0s, 10s, …, 70s. We then gave a fresh Gemini 4 Carbon analysis session only that eight-frame contact sheet and the transcript, asking for an overall summary, a breakdown of each 10-second window, and a standalone highlight. Its recorded inputs contain neither the denser frames nor the audio file used for the separate audit. Eight stills describe those eight moments; they cannot establish everything that happens between them.

Try this prompt
In ChatCut Desktop, create a new 1920x1080 24fps project named 'Blog · Q3 · can-gemini-watch-videos', import teaser-gemini.mp4, wait for its word-timed transcript, and extract frames every 10 seconds from 0s to 70s. Summarize what the whole 73-second video is about and what is spoken and visible on screen in every 10-second window. Don't edit the timeline yet.

The import began at 13:46:01 and transcription was confirmed complete by 13:46:55, under a minute later in this run. The overview contains eight labeled source frames from 0.000s to 70.000s:

Eight-frame contact sheet sampled every 10 seconds from 0.000s to 70.000s of the 73.5-second 1920x1080 loft video, showing a presenter in glasses and a burnt-orange shirt in front of sloped wood rafters, an upper-left skylight, and a right-side brick gable window, gesturing at 10s, holding both open palms wide at 20s, blinking at 30s, gesturing at chest height at 40s and 50s, lifting one hand at 60s, and looking down toward the desk at 70s.
Saved 10-second contact sheet (0.000s to 70.000s): a consistent loft composition, a wide gesture at 20.000s, and a downward glance at 70.000s.

Combining those eight frames with the word-timed transcript, Gemini identified raw talking-head A-roll with multiple false starts. It correctly noted that the sampled images contained no motion-graphics overlays despite the speaker referring to graphics in the video. The table summarizes the original blind-pass response, with the later audit distinguishing visible details from guesses.

WindowSpeech in Gemini’s transcript-based summaryGemini’s visual report and our audit
0–10sIntroduces AI Motion Graphics, then refers to graphics supposedly in the video.Presenter in a wood-beamed loft; hands low at 0s and gesturing by 10s. No overlay in these samples.
10–20sNames editing software; Gemini flagged “cars” as a likely mishearing of “cards.”It connected this suggestion to the wide two-handed gesture at 20s. That is a contextual hypothesis, not proof of the spoken word.
20–30sAbandons a take and restarts the point about graphics for talking-head videos around 24.32s.Wide palms at 20s; one-hand gesture and closed eyes at 30s.
30–40sFinishes the point around 34.93s, pauses, and restarts.Hand gesture at 40s. The two samples do not establish silence between them.
40–50sSeveral incomplete phrases and pauses.Presenter faces the camera at 50s.
50–60sAnother unfinished line and a pause.Gemini said he “stays locked onto the camera.” The denser audit shows downward gazes at 51–52s and a forward lean at 58s, contradicting continuous eye contact.
60–70sA false start precedes the closing line about ChatCut’s AI around 62.54–68.38s.Raised hand at 60s; looking down by 70s.
70s–endNo further words appear in the transcript.Gemini acknowledged that only the 70s frame was supplied. It could not observe the later reach toward the camera.

Step 3: Ask Gemini to pick the strongest ~15-second standalone short clip

With the transcript and overview available, ask for a self-contained highlight before making cuts. Treat “best” as an editorial choice to review, not an objective score:

Try this prompt
From that breakdown, pick the strongest ~15-second selection, using one or two ranges if needed, that works on its own as a short video for a cold viewer. Give exact start and end source timestamps, the exact words to keep vs. cut, and why it beats the other sections.

Gemini selected the two speech ranges below and explained why it skipped the opening: “Thirdly” depends on earlier context, and the claim about graphics already on screen does not match the sampled raw footage. Its choice forms a problem-to-solution passage; “best” remains an editorial judgment. After retaining natural breaths and small boundary pads, the finished landscape clip is 16.9 seconds, slightly longer than the approximately 15-second target:

  • Keep Part 1 (24.32s – 34.93s): “These graphics can be so important when you are making a talking-head informational video. And they are so hard to make. And it doesn’t have to be the case anymore.” (Hook → Pain Point → Pivot.)
  • Remove the intervening retakes: The speech boundaries span 34.93s–62.54s (27.61 seconds). With retained audio padding, the committed clip boundaries are about 35.13s and 62.50s, so the removed media interval is about 27.37 seconds.
  • Keep Part 2 (62.54s–68.38s, speech): The closing line about ChatCut’s AI visualizing what the speaker says. The committed edit retains a little surrounding audio, ending near 68.54s.

Step 4: Cut the retake block from the transcript and disguise the splice with a 1.09× punch-in

Gemini edited the timeline through ChatCut’s transcript-based editing workflow in the video editor, previewed the two selected ranges, and committed the cut:

Try this prompt
Cut the timeline to keep 24.32s–34.93s ('These graphics can be so important... doesn't have to be the case anymore.') followed immediately by 62.54s–68.38s ('ChatCut's AI will be able to help you visualize everything you're saying on screen very clearly.'). Preserve his natural sentence breaths so we don't create extra jump cuts, smooth the audio splice, and add a subtle 1.09x medium close-up punch-in on the second clip so the single cut looks intentional.

Gemini preserved the natural sentence breaths and committed two clips, with a splice at timeline frame 260 (10.83s). The original tool calls confirm a 1.09× punch-in on the second clip (2093×1177 over the 1920×1080 canvas), plus short audio fades. The first clip ends at source 35.125s, before the audio burst measured at 35.45s. The delivered video has 405 frames at 24 fps: a video-stream duration of 16.875 seconds. Its MP4 container is 16.894 seconds because the audio ends slightly later.

Two rendered frames around the committed splice: f253 shows wider framing, and f266 shows a closer view with the corrected ChatCut's AI caption.
Gemini kept two clips and applied a 1.09× punch-in to the second. The transition is at frame 260; the removed source interval is about 27.37 seconds after retained padding.

Step 5: Style word-timed captions and fix speech-recognition homophones

Automatic speech recognition transcribed the brand name as “checkouts.” Gemini applied the published Studio Clean word-highlight template and corrected two displayed caption cards to “when you are making a talking-head” and “ChatCut’s AI will be able to help.” The original caption readback records Inter Tight, weight 800, with a white active-word background. The correction receipts explicitly apply to caption display, leaving the underlying speech edit intact. The before/after images show the change on the same timeline frame.

Try this prompt
Enable captions on the cut timeline using the Studio Clean word-highlight preset, then check every caption card against what the speaker actually meant and fix speech-recognition errors like 'checkouts. AI Will be' -> 'ChatCut's AI will be' and 'talking head' -> 'talking-head'.
Side-by-side comparison of timeline frame 266 (11.08s) before and after caption text repair: left image reads 'checkouts. AI Will be able to help' from raw speech recognition; right image reads 'ChatCut's AI will be able to help' in the Studio Clean active-word highlight style.
Left: raw ASR output ('checkouts. AI Will be able to help'). Right: corrected Studio Clean caption card ('ChatCut's AI will be able to help') verified on timeline frame 266.

Step 6: Inspect composed frames, balance loudness, and export 1080p MP4

Gemini reviewed nine composed frames, raised both dialogue clips by +3.0 dB, and measured the mix changing from -21.9 LUFS to -18.9 LUFS. It then exported a local 1080p, 24 fps H.264 MP4 and an SRT containing nine cues, including the corrected brand name. The export task completed successfully; the web copy was subsequently compressed. The delivered MP4 independently measures -18.9 LUFS integrated with a true peak of about -1.3 dBTP, and is 4.59 MB (4.38 MiB), H.264/AAC. These measurements describe this export, not a universal loudness target or proof that every splice sounds good.

Try this prompt
Render a 9-frame contact sheet and audio loudness check across the finished short clip to verify that no hand gestures or loft windows are cropped and all captions are readable. Lift dialogue loudness to around -19 LUFS, export a 1080p 24fps MP4 and SRT file, and check ChatCut billing to confirm exact credits spent.
Nine saved composed frames from f0 to f404 of the 16.9-second landscape clip. Wide palms are visible at f0 and f354; f404 shows the presenter looking downward. Captions appear on some, not all, sampled frames.
Nine-frame review: the sampled gestures fit within the landscape frame. The last sample already shows a downward glance, so review the ending before publishing.

The original post-export billing receipt, checked at 14:04:19 UTC+8 on November 18, reports 0.00 ChatCut credits for this project: conversation and generation totals are both zero. That supports the project-scoped result for this import, analysis, cut, captions, and export run. It is not an account-wide zero-spend statement, a final settlement guarantee, or evidence that Google’s reasoning usage was free. Antigravity’s own allowance or charges remain separate. For another workflow, see turning long videos into shorts.

What did Gemini get right — and what did it get wrong on our 73-second video?

We compared the isolated 10-second blind pass against denser source frames, the audio, and actual edit receipts. The separate audit filled in the remaining integer-second samples through 73s; together with 0s, that is 74 sampled timestamps, not 73. Scene-cut detection analyzed 1,752 frames and returned no detected cuts at threshold 0.3. The session also read an extracted audio track and measured 50 ms RMS dBFS windows around candidate cut boundaries. This audits Gemini’s selected-frame workflow in Antigravity; it does not measure native video-upload accuracy in Gemini Apps or the API.

Nine source samples: 0s, 6s, 10s; 50s, 58s, 60s; 66s, 70s, 72s. They show raised hands at 6s, a forward lean at 58s, wide palms at 66s, a downward glance at 70s, and an arm reaching toward the camera at 72s.
Additional samples reveal actions absent from the 10-second overview. The frames show posture and gestures; they do not prove why the presenter leaned forward or reached toward the camera.

What did Gemini get right in the blind pass?

  1. Separated spoken claims from visible overlays. Gemini noticed that the presenter refers to motion graphics, while none appear in the eight supplied samples. Those images support the observation about sampled moments; they do not alone prove every frame of the recording lacks overlays.
  2. Flagged two likely ASR errors before editing captions. It suggested “cards” for “cars” around 18.60s, and “ChatCut’s” for “Checkouts” at 60.78s and 62.54s. The later caption correction and exported SRT confirm the brand-name repair. “Cards” remains a plausible contextual suggestion; the hand gesture by itself cannot verify the audio.
  3. Chose a self-contained problem-to-solution passage. Its original answer selected 24.32–34.93s plus 62.54–68.38s, identified the intervening retakes, and explained why “Thirdly” is a weak standalone opening. The committed timeline confirms that Gemini used those speech ranges with small audio pads, rather than merely suggesting an edit.

What did Gemini miss or infer incorrectly?

  1. Invented continuous eye contact from two endpoints. Gemini wrote: “Between 50.000s and 60.000s he stays locked onto the camera”. The denser frames show downward gazes at 51–52s, broad hand gestures at 54–55s, and a forward lean at 58s. The continuous-eye-contact claim was wrong. The images do not establish that the presenter was reading notes or how far he moved in physical space.
  2. Could not see gestures between its samples. The 6s, 54s, and 66s frames show broad gestures absent from the eight-frame overview. The 66s gesture falls inside the retained second clip. A centered 9:16 crop of a 1920×1080 source keeps only about 608 pixels of width, so these are useful moments to inspect before choosing a vertical crop. We kept the landscape canvas.
  3. Described transcript gaps as silence without audio evidence. The blind response calls 34.93–39.17s a silent pause. The separate audio measurement shows a -18.1 dBFS RMS burst in the 50 ms window starting at 35.45s, up from -53.1 dBFS in the preceding window. That disproves clean silence; the level alone does not identify the sound as a cough. Denser frames also show a hand touching the head at 17s and a reach toward the camera at 72s, actions the sparse overview could not show.

Sparse frames support claims about the sampled moments. They leave events between samples uncertain; increasing sampling and listening to the relevant audio can resolve some of those gaps.

What you still need to check yourself (plus copyable prompts and fixes)

Whenever you use Gemini to watch a video and plan an edit — whether in gemini.google.com or inside Antigravity + ChatCut — run two quick checks before publishing:

  • Zoom in to 0.5s–1s frames around every cut boundary and crop decision. Use coarse 10-second frames to map a long recording, then pull dense frames across the 15-second stretch you actually plan to keep so wide hand gestures, blinks, or lean-ins don’t surprise you.
  • Listen to transcript gaps and splice tails. Coughs, breaths, mic bumps, and chair sounds may occur without recognized words. Adjust padding to the actual recording rather than relying on one fixed duration.

Use these two copyable prompts to keep Gemini honest on any local recording in Antigravity + ChatCut:

Try this prompt
Inspect 12 evenly spaced overview frames and the full word-timed transcript of my video in ChatCut. Separate (1) spoken words, (2) details directly visible in a numbered frame, and (3) anything unknown because it happened between sampled frames. Never assume steady eye contact or static framing between two samples.
Try this prompt
Before cutting my chosen highlight clip ([start] to [end]), sample source frames every 1 second inside that window and run an audio check across the cut boundaries. Tell me if any wide hand gestures would be clipped by a 9:16 crop or if any coughs/noise sit inside the surrounding pauses.

Troubleshooting common snags:

  • Gemini Apps cannot answer about a YouTube video. Check Keep Activity, use a regular chat instead of Live or Google Messages, and ask Gemini to find the public video first (YouTube help). The API’s private/unlisted restrictions should not be presented as an Apps-specific rule.
  • A file upload fails. “Delete data to upload file” concerns stored chat data; remove only history you no longer need under Settings → History, or contact your Workspace administrator. “Your uploads may be too large for the best results” concerns analysis quality/context; try a smaller relevant excerpt. The file-upload guide distinguishes these cases.
  • The editor tools do not appear in Antigravity. Follow the connection instructions, check the ChatCut connection, and start a new conversation after setup. Do not assume an already-open conversation has loaded a newly installed connection.

Frequently asked questions about Gemini watching videos

Can Gemini watch YouTube videos from a link?
Gemini Apps can find YouTube videos and answer questions about their content with Keep Activity enabled; this feature is unavailable in Live and Google Messages. You can try a public link, but the Apps help page does not guarantee every URL or visual detail. The Gemini API separately documents direct public YouTube URL input.
How long of a video can I upload to Gemini?
Google's Gemini Apps attachment guide lists 2 GB per video and 5 minutes of combined video, rising to 1 hour on Google AI Pro or Ultra. Up to 10 supported files can be attached per prompt, subject to availability. API limits are separate and depend on file input method and model context.
Does Gemini actually watch the video or just read the transcript?
The Gemini API supports visual frames and audio, with default static sampling at 1 FPS and opt-in timeline navigation on specific supported models. The Apps YouTube help page does not explain its frame-processing method. Our Antigravity test uses selected stills plus a transcript, so it is not a native Gemini video-upload benchmark.
What video file formats does Gemini accept?
The Gemini API lists MP4, MOV, WebM, AVI, MPEG, MPG, WMV, 3GPP, and FLV MIME types. The consumer Apps guide does not provide the same exhaustive list. Check the relevant surface rather than assuming API format support is an Apps guarantee.
Can Gemini watch TikTok, Instagram Reels, or Google Drive videos?
The sources cited here establish a YouTube integration, not a general guarantee for TikTok or Instagram URLs. For supported Drive files, use Add files and Add from Drive with History enabled and Google Workspace connected. For other sources, use an authorized local file and check the attachment limits.
Can Gemini watch a video and edit out the best clips automatically?
The cited Gemini analysis guides do not establish a local multi-track editor. In our test, Gemini 4 Carbon in Antigravity selected two speech ranges, cut them in ChatCut Desktop, corrected captions, and completed a 1080p MP4 and SRT export. You should review the selected ranges, captions, framing, and audio before treating the output as finished.
Does watching and cutting a local video in Antigravity and ChatCut cost credits?
ChatCut's published policy says an external Agent uses its own subscription or API allowance for reasoning; ChatCut credits cover ChatCut-hosted generation. Uploads, transcription, standard caption editing, and local export do not themselves use credits. Cloud exports include a free allowance; beyond it, they follow ChatCut's current credit rules (see Web vs Desktop Export). Our November 18 Antigravity run has an original post-export billing receipt reporting 0.00 ChatCut credits for this project, with both conversation and generation totals at zero. This is the recorded project total at that check, not a claim that Google reasoning or all account activity was free.
Three ways to try ChatCut
Edit local files on your computer For long footage, screen recordings and 4K exports. macOS and Windows. Download DesktopDownload for macOSDownload for WindowsOpen in your browser
On a computer, download ChatCut Desktop.
Start in your browser Free plan, nothing to install. The editor opens with this prompt: Import my raw video in ChatCut, summarize every 10 seconds from its transcript and frames, pick the strongest 15-second standalone clip, cut out retakes, add Studio Clean captions, and export 1080p. Try this prompt
Already using an AI agent? Send this one message to the agent you use.
Read ChatCut.io/antigravity to install ChatCut
Send it in a new Antigravity conversation. Setup guide

Checking your footage...

Less editing. More creating.

Download ChatCut Desktop free and make your first video today.

Download Desktop Download for macOS Download for Windows Try it for free