NewVision-in-the-loop editing: the AI now edits to what it sees
AI video editor

Rawfootagein.Scroll-stoppingshortsout.

An editor that watches your clip, finds the hook, cuts the dead air, reframes to the speaker, and captions it, then ships platform-ready Reels, Shorts, and TikToks in multiple takes.

No credit card/Private to your workspace/9:16 · 1080x1920
founder-clip.mp4 · Reelsmith.video Studio
Detecting hook
Variants
Safe Professional
···
High-Energy
···
Hook-Led
···
Timeline0:07 / 0:32
V1
A1
YouTube ShortsInstagram ReelsTikTokPodcast clipsTalking-headProduct demosFounder contentTutorialsWebinarsCourse clipsYouTube ShortsInstagram ReelsTikTokPodcast clipsTalking-headProduct demosFounder contentTutorialsWebinarsCourse clips
Trusted by creators
0
Creators on Reelsmith.video
0
Projects created
0
Reels rendered
New creators · 14 days
6creators building right now
Before / After

Raw footage in, scroll-stopping reels out.

The same clip, before and after Reelsmith.video. No manual editing: it reframes to the speaker, cleans the audio, captions every word, and grades the shot for you.

Talking-head reel. Auto-reframed to the speaker, captioned word by word, dead air cut, colour graded.
Founder / brand clip. Hook up front, 9:16 crop with a subtle push-in, captions and clean audio, polished grade.
Everything Reelsmith.video added, automatically
Hook up frontActive-speaker 9:16 reframeSubtle push-in & punch zoomWord-by-word captionsKeyword highlightDead air & filler cutBackground blurNoise reductionBeat-synced cutsSound effectsAuto b-rollColour gradeBrand intro & outroDeeper voice (optional)
Made with Reelsmith.video

Real reels, straight from the editor.

View the gallery →
What it does

Not a template. An editor that makes decisions.

What to cut, where to zoom, which moment to open on, then it reviews its own cut and fixes what’s off.

Finds your hook

We transcribe your footage and open on the strongest moment, front-loaded for the scroll.

Cuts the dead air

Silences and filler words (“um”, “uh”) are trimmed to the word. Every second earns its place.

Captions that read

Word-by-word captions with keyword emphasis, built strictly from what was actually said.

Reframes to the speaker

A 9:16 crop that follows the subject, with measured push-in and punch zooms on the beats.

Beat-synced & ducked

Tempo detection snaps cuts to the beat; music ducks under speech automatically.

Edits to what it sees

A vision model reads your actual frames - favouring the sharp, well-framed takes and keeping the speaker's face centred, never half-cropped. On every plan.

Reviews its own cut

Every render gets a self-review pass that flags awkward cuts or unreadable captions and re-renders to fix them. Same on Free as on Studio.

Multiple variants

Every upload returns several editorial takes (safe, high-energy, hook-led), so you choose.

How it works

You upload one file. You get three finished reels.

No timeline to learn and nothing to set up. This is the same pipeline that runs on every upload, start to finish.

LiveEvery stage above runs on your footage, in this order, on every upload.
01Takes about 20 seconds

Drop in the raw file

One clip, straight off your phone or a two-hour podcast. Pick a style and you are done.

02Runs on its own

It watches, then edits

Finds the hook, cuts the dead air, keeps the speaker centred, writes the captions, grades the colour, then reviews its own cut and fixes what is off.

03Ready in minutes

Pick the take you like

Three finished 9:16 cuts of the same footage, each a different angle on it. Post one, or open the timeline and change anything.

No credit card to sign up.
Editing styles

A style for every format.

Pick the treatment that fits your content; we adapt the cuts, captions, and pacing to match.

Talking-head viral editSkit / ComedySplit screen viralMy style (cloned from a reel)Podcast clipFounder / personal brandProduct demoScreen demoEducationalMeme / fast-pacedClean corporateLinkedIn / professionalInterviewWedding filmScenic / travelPersonal brandingMotivationalGaming / sports highlightsAesthetic / lifestyle montageAction / fast montageReal estate listingDocumentary
Pricing

Same AI quality on every plan.

Every plan runs the exact same AI editor: vision-aware planning that edits to what's on screen, active-speaker auto-reframe (face always centred), word-by-word captions, beat-synced cuts, colour grade, and a self-review QC pass. Plans differ only on how much you make, how long your source can be, upload size, and the Free watermark - never on quality.

Starter

$8.99/mo

Your first paid step

billed monthly

  • 9 takes / mo (3 renders)i1 render consumes 1 from your quota and produces 3 takes - 3 ready-to-post videos.
  • 30 source minutes / mo
  • 30-min max source · 2 GB uploads
  • Manual fine-tune editor
  • No watermark
  • Add-on minute & render packs
  • Monthly billing only
Most popular

Creator

$26/mo

For regular creators

billed yearly, save 10% (~1 month free) · or $29/mo monthly

  • 30 takes / mo (10 renders)i1 render consumes 1 from your quota and produces 3 takes - 3 ready-to-post videos.
  • 100 source minutes / mo
  • 60-min max source · 6 GB uploads
  • Manual fine-tune editor, no watermark
  • Competitive benchmark vs top videos
  • Brand kits
  • Files kept while subscribed

Studio

$89/mo

For teams & full podcasts

billed yearly, save 10% (~1 month free) · or $99/mo monthly

  • 90 takes / mo (30 renders)i1 render consumes 1 from your quota and produces 3 takes - 3 ready-to-post videos.
  • 500 source minutes / mo
  • 150-min max source · 12 GB uploads
  • Everything in Creator
  • Priority rendering
  • Team workspace

Add-on packs (paid plans): minutes +30 / $9 · +100 / $29 - takes +30 / $9 · +120 / $29.

Built to make every reel scroll-stopping - punchy cuts, dynamic captions and a professional finish.

Developer API

Automate it with the API and MCP.

Upload footage and fetch finished reels programmatically over a clean REST API, or let AI agents drive it through the built-in MCP server (Claude and other MCP clients). Create a key, authenticate with a bearer token, and go. Usage counts against your normal plan quota, with nothing extra to buy.

Endpoints
  • POST /api/v1/videos - create + get an upload URL
  • POST /api/v1/videos/{id}/finalize - start processing
  • GET  /api/v1/videos/{id} - status + output URLs
  • GET  /api/v1/videos - list your videos
# 1. Create a video (returns a presigned upload URL)
curl -X POST https://reelsmith.video/api/v1/videos \
  -H "Authorization: Bearer $REELSMITH_KEY" \
  -H "Content-Type: application/json" \
  -d '{"title":"My clip","platform":"YOUTUBE_SHORTS",
       "editingStyle":"TALKING_HEAD","filename":"in.mp4",
       "contentType":"video/mp4","byteSize":52428800}'

# 2. Upload bytes -> 3. finalize -> 4. poll GET /api/v1/videos/{id}
# when status = READY, "outputs" has each take's downloadUrl
MCP server for AI agents

A built-in Model Context Protocol server at /api/mcp. Point Claude or any MCP client at it with your key and it can create, track, and fetch videos. No server to host.

Secure by design

Hashed API keys, workspace-scoped access, per-key rate limiting, strict input validation, and responses that return only signed, short-lived media URLs. No secrets or storage keys are ever exposed.

Your next short is one upload away.

Turn the footage you already have into edits worth posting in minutes, not hours.