VidTL - The Editor That Edits For You

Media Library

Click "+ Import" to add videos

Project Settings

Project Name

Resolution

Width

Height

Frame Rate

Audio

Sample Rate

Changes to resolution and frame rate will affect all clips. Audio settings apply to new exports.

Program Monitor

Ready

00:00.000

Import subtitles to edit

Clip Properties

Video Clip

Select a clip to view properties

Timelines

Tracks

Noise Suppression

Reduce steady background noise and static locally in your browser.

Audio clips to process 0

Selected video clips use their linked audio when available.

Analyzing selected audio...

How much to take out --

Set automatically from the clip you picked. Higher takes out more background, but the more you take out the less natural the voice sounds.

Extra smoothing --

Set automatically from the clip you picked. Helps with leftover hiss on noisy recordings, but roughens the voice, so it stays off unless it is needed.

Replace selected audio clips on the timeline

The processed WAV is also added to the media library.

Connect a coding agent

Let an AI agent running in your terminal (like Claude Code) edit this project for you. Create an access key, hand it to your agent, then turn on agent control below and click Apply. You can watch every change live and undo anything.

Access key

You have no access key yet.

Set up your agent

1. In your terminal, download the connector:

curl -O https://vidtl.com/app/cli/vidtl.mjs

2. Give your agent the key:

export VIDTL_API_KEY=<your access key>

3. Ask your agent to start with:

node vidtl.mjs instructions

4. Using Claude Code? Run this once per project so your requests are always logged word for word:

node vidtl.mjs install-hook

Session control

Allow my agent to control this editor

While this is on, your connected agent can see and edit this project. Only one editor tab can be controlled at a time.

Agent control is off.

Remove Silence (Local)

Detects and removes silence using waveform analysis.

Apply to all clips on timeline (including video clips)

When unchecked, only processes selected clip(s)

Only process talking-head clips (skip b-roll)

Uses subtitle density to detect talking-head clips and skip b-roll footage

Silence Threshold (dB) Auto

Auto

Min Silence Duration (seconds)

0.3

Pre-head (seconds)

0.0

Negative = cut into audio, Positive = leave padding

Post-tail (seconds)

0.0

Cut to the Beat

Select your music clip plus the video or image clips for the montage. The editor listens for the moments that punch — vocals coming in, drum hits, drops — and cuts your clips so every transition lands on one, the way music videos are cut.

Scene Detection

Finds the camera cuts inside your footage so long recordings can be split into separate scenes automatically.

Apply to all video clips on the timeline

When unchecked, only the selected clip(s) are analyzed

Sensitivity

Higher finds more cuts, lower only finds strong cuts

Minimum scene length (seconds)

Multi Cam Auto Cut

Select your synced camera clips. The editor listens for who is speaking and cuts between cameras automatically. Line the clips up first with Multi Cam Smart Sync.

Minimum shot length (seconds)

2.5

Shorter values switch cameras more often

Keep audio from all cameras

When unchecked, you only hear the camera that is on screen

Auto Zoom

Made for screen recordings. Select the recording, and the editor finds the moments where something happens on screen — clicks, typing, windows opening — and zooms in on that spot automatically. Any zoom animation already on the clip is replaced.

Zoom amount

1.5

How far to zoom in on the action

Sensitivity

Higher reacts to smaller on-screen changes

Normalize Audio

Brings your clips to the same comfortable loudness — quiet clips come up, loud ones come down, and nothing distorts. Works on the selected clips, or every audio clip when nothing is selected.

Remove Camera Shake

Steadies shaky handheld footage. Select the shaky clip first. The steadied video is saved to your media library — this can take a while, so it works best on short clips.

Strength

Higher handles bigger shakes but may crop in more at the edges

Replace the clip on the timeline

The original file stays in your media library

Remove Green Screen

Takes a plain coloured background out of the clip, so whatever sits below it on the timeline shows through instead. The picture updates as you adjust.

Background colour

How much colour goes 30

Raise it until the whole background disappears.

Edge softness 20

How gently the background fades out around your subject.

Colour spill 50

Takes the background colour back out of hair and edges it has tinted.

Edge trim 0

Move right to shave off a leftover outline, left to keep more of your subject.

Edge blur 0

Softens the cut-out edge so it blends into what is behind it.

Background cleanup 0

Clears faint patches of background that will not go away.

Subject cleanup 0

Fills in see-through patches in your subject.

Show

Result Cut-out Original

The cut-out shows what is kept in white and what goes in black, which makes stray patches easy to spot.

Voice Isolation

Separates the voice from music, noise, and background sound. Select the clips to clean up first. The separated audio is saved to your media library. The first use downloads the separation model, and processing takes a while for long clips.

Replace the audio on the timeline

The original audio stays in your media library

Keep the music & background sound on its own track

Splits the sound in two: the voice stays here, and everything else goes to a separate audio track so you can turn it down or delete it later

Background Removal Options

Lower sensitivity keeps more of the subject when the mask removes too much.

Sensitivity

50%

Lower keeps more of the subject. Higher removes more uncertain pixels.

Edge feather

0.0px

Softens the transparent edge after the mask is created.

Background Removal Preview

Before

After

Generate Subtitles (Priority)

Select one or more clips on the timeline to generate subtitles with word-by-word timestamps.

Link subtitle clips to source clip in a group

Text to Speech

Convert text to speech using different AI models. Maximum 5000 characters.

Model

Voice

Quality Preset

Voice to copy *

Pick a recording of the person talking. A few clear seconds of just their voice works best.

Words spoken in it *

The voice copies best when these match what is said, word for word.

Skip the words (faster, but sounds less like the voice)

Expression

Exaggeration 0.50

How emotional the voice sounds. 0.5 is neutral; higher feels more dramatic.

Pacing 0.50

Lower values slow down the pacing; higher values stick closer to the reference style.

Temperature 0.80

How varied the speech sounds across generations.

Seed

Use the same seed to repeat a result. 0 picks a new one each time.

Text to Synthesize *

0/5000 characters

Choose a voice to copy

Pick a clip or recording where the person talks clearly.

Generate Music

Generate original music from a text description — either a full song with singing, or an instrumental backing track.

Description *

Describe the mood, instruments, tempo, and genre. The more detail you give, the closer the result. 0/2000

Type of music

Full songs can include singing and run up to 5 minutes. Background music is always instrumental and finishes faster.

Longest length (seconds)

The most the track can run. Music ends when it reaches a natural finish, so adding more sections above is what makes it longer.

Song structure (optional)

Lay the song out in sections, each on its own line: [intro], [verse], [chorus], [bridge], [instrumental], [solo], [outro]. Any words you write under a section get sung. Sections with no words stay instrumental. More sections make a longer track.

Leave this empty for instrumental music and the sections are built for you.

These settings only apply to background music.

Temperature: 1.0

Higher values produce more variety; lower values stay closer to the prompt.

Guidance: 3.0

How strongly the prompt steers the result. Higher = more faithful to the description.

Top-K: 250

Limits sampling to the K most likely choices. Set to 0 to disable.

Top-P: 0.0

Use nucleus sampling instead of Top-K. Set to 0 to disable.

Seed

Leave at -1 for random. Use a fixed number to reproduce a result.

Generate Video (AI)

Create a brand-new video clip from a text description. This is the slowest, most demanding option — try stock footage, your own uploads, and motion graphics first.

Description *

Describe the scene, subject, camera, and style. 0/2000

Avoid (optional)

Things you do not want to appear in the video.

Model

LTX 2.3 is currently available.

Seed

Leave at -1 for random. Use a fixed number to reproduce a result.

Width

Height

Frame rate

Length (frames)

Total frames. Seconds = frames ÷ frame rate.

Steps: 8

More steps can improve quality but take longer.

Guidance: 1

How strongly the description steers the result.

Denoise: 1

Keep at 1.0 for fully generated video.

Sampler

Scheduler

Starting Image (optional)

Optional. The video will animate from this image (image-to-video).

Generating video uses a large amount of your usage allowance and can take several minutes.

Auto B-Roll (Pexels)

Uses your existing subtitle clips to find matching stock video and place it on the timeline.

Segment Length (seconds)

Max Segments

Results Per Segment

Fallback Query

Place clips on a new "B-Roll" track Use fallback query if no results

FFmpeg

Run custom FFmpeg commands on your media files.

Note: Input files can be any size, but output files are capped at 2GB to prevent browser issues.

Available Media Files

Click a file to insert its name into the command

FFmpeg Command

Filenames with spaces will be automatically quoted

Output Filename (optional)

Used if not specified in command

Quick Examples

Extract audio 10s clip @ 5s First 30s Remove audio Replace audio Scale to 720p

Tip: -ss before -i for faster/accurate seeking

Export Video

File Name

Timeline

Where to make it

On this computer Uses this computer. Keep the tab open while it works. On our servers Makes the video on our computers instead of yours. It comes out exactly the same, and you can close the tab.

Format

Resolution

Quality

Higher quality = larger file size. For ProRes, this selects different quality levels.

Transparent background

Available for WebM exports. Empty canvas areas stay transparent.

Audio Channels

Use Mono if your exported video only has audio in one speaker

Split into separate files at markers

Each section between markers downloads as its own video — great for chapters and short clips. Not available for GIF.

Rebuild the whole video from scratch

Exporting again normally reuses the parts of your video that have not changed, which is much faster. Turn this on to build every part again.

Also create these sizes

Widescreen 16:9 (1920×1080) Vertical 9:16 (1080×1920) Square 1:1 (1080×1080)

One video downloads per checked size. The picture is scaled to fill each size and centered, so the edges may be trimmed. Not available for GIF.

Video Settings

Video Codec

Frame Rate

Encoding Preset

Pixel Format

Rate Control

Tune (H.264 / H.265)

Keyframe Interval (seconds)

Audio Settings

Audio Codec

Audio Bitrate

Sample Rate

Channels

Normalize loudness (automatic volume balancing)

Select a platform preset to automatically configure optimal settings

Desktop computer required

Noise Suppression

Connect a coding agent

Remove Silence (Local)

Preview

Cut to the Beat

Hits Found

Scene Detection

Scenes Found

Multi Cam Auto Cut

Auto Zoom

Normalize Audio

Remove Camera Shake

Remove Green Screen

Voice Isolation

Background Removal Options

Background Removal Preview

Before

After

Track Moving Object

Generate Subtitles (Priority)

Text to Speech

Choose a voice to copy

Generate Music

Generate Video (AI)

Auto B-Roll (Pexels)

FFmpeg

Export Video

Video Settings

Audio Settings

Export Timeline (FCP 7 XML)

About VidTL Editor

Desktop computer required

Editor Paused

Keyboard Shortcuts

Noise Suppression

Connect a coding agent

Remove Silence (Local)

Preview

Cut to the Beat

Hits Found

Scene Detection

Scenes Found

Multi Cam Auto Cut

Auto Zoom

Normalize Audio

Remove Camera Shake

Remove Green Screen

Voice Isolation

Background Removal Options

Background Removal Preview

Before

After

Track Moving Object

Generate Subtitles (Priority)

Text to Speech

Generate Music

Generate Video (AI)

Auto B-Roll (Pexels)

FFmpeg

Export Video

Video Settings

Audio Settings

Export Timeline (FCP 7 XML)

About VidTL Editor