VDOGEN

Spec sheet

What it does

VDOGEN is an AI video editor built around editing a transcript instead of dragging a timeline.Read 15 Oct 2026 · vdogen.com

Product

VDOGEN is an AI video editor that edits video through its transcript rather than a timeline.Read 11 Oct 2026 · vdogen.com

Intended users

The workflow describes use by solo creators, marketing teams and education teams.Read 15 Oct 2026 · vdogen.com

Free plan

YesRead 21 Sep 2026 · vdogen.com

Integrations

The documented AI stack includes OpenAI Whisper, OpenAI translation, fal.ai models and ElevenLabs services.Read 15 Oct 2026 · vdogen.com

AI generation

Features include AI image generation, voice-over, background music, sound effects, talking avatars, and script-to-video.Read 11 Oct 2026 · vdogen.com

AI image generation

Text prompts can generate B-roll, thumbnails and explainer visuals through FLUX on fal.ai.Read 15 Oct 2026 · vdogen.com

AI music

Users can generate background music from a described mood and place it on the multitrack timeline.Read 15 Oct 2026 · vdogen.com

AI sound effects

Text descriptions can be turned into sound effects that are layered at chosen timeline positions.Read 15 Oct 2026 · vdogen.com

AI voice-over

ElevenLabs text-to-speech creates narration, corrected takes and alternate reads.Read 15 Oct 2026 · vdogen.com

API keys

The site says users can bring their own OpenAI and fal.ai API keys, which remain in their environment and are not stored by VDOGEN.Read 11 Oct 2026 · vdogen.com

Automatic captions

YesRead 21 Sep 2026 · vdogen.com

Automatic captions

Whisper transcription supplies word-level timing and speaker detection for captions.Read 15 Oct 2026 · vdogen.com

Bring-your-own keys

OpenAI and fal.ai keys can be supplied by users and remain in their environment rather than being stored by VDOGEN.Read 15 Oct 2026 · vdogen.com

Caption exports

Caption files can be exported as SRT, VTT, plain text or FCPXML.Read 15 Oct 2026 · vdogen.com

Cleanup

The editor can detect silence and remove filler words such as “um,” “uh,” and “basically.”Read 11 Oct 2026 · vdogen.com

Early-access status

The features page labels VDOGEN as early access and invites users to request access.Read 15 Oct 2026 · vdogen.com

Exports

It exports captions as SRT, VTT, plain text, or FCPXML, and can export video as MOV or MP4.Read 11 Oct 2026 · vdogen.com

Extensibility

The comparison page says model choices are overridable through environment variables and points to a README for the full list.Read 15 Oct 2026 · vdogen.com

Filler removal

The editor detects common fillers such as um, uh, ah, like, basically and you know for one-click removal.Read 15 Oct 2026 · vdogen.com

Free-tier limit

The comparison page lists the free tier as three exports per month.Read 15 Oct 2026 · vdogen.com

Limit: platform coverage

The pages reviewed describe web use and self-hosting but do not document native iOS or Android apps.Read 15 Oct 2026 · vdogen.com

Limit: pricing transparency

The maker's comparison publishes a Starter price, while the main pricing page was not retrievable during this research session.Read 15 Oct 2026 · vdogen.com

Limit: public API

The pages reviewed document provider keys and environment-variable overrides, but do not present a standalone VDOGEN REST API or SDK.Read 15 Oct 2026 · vdogen.com

Local processing

The site says FFmpeg runs on the user's infrastructure and video files stay local unless exported.Read 15 Oct 2026 · vdogen.com

Multitrack timeline

BGM, sound effects and voice-over tracks support per-track mute, volume and clip positioning.Read 15 Oct 2026 · vdogen.com

Platform presets

Presets target YouTube Shorts, Instagram Reels, TikTok, LinkedIn, YouTube and Instagram Feed.Read 15 Oct 2026 · vdogen.com

Presets

Platform presets are listed for YouTube Shorts, Instagram Reels, TikTok, LinkedIn, YouTube, and Instagram Feed.Read 11 Oct 2026 · vdogen.com

Scene detection

FFmpeg scene-change detection marks visual boundaries for segmentation.Read 15 Oct 2026 · vdogen.com

Script-to-video

A script, voice and style can produce generated images, narration and Ken Burns segments automatically.Read 15 Oct 2026 · vdogen.com

Self-hosting and licence

The maker describes the project as self-hostable and open source, using Next.js and Electron.Read 15 Oct 2026 · vdogen.com

Semantic cuts

Deleting words, sentences or transcript blocks recompiles the video with smart cuts.Read 15 Oct 2026 · vdogen.com

Silence detection

Silence detection uses configurable noise and duration thresholds and previews detected ranges.Read 15 Oct 2026 · vdogen.com

Silence removal

YesRead 21 Sep 2026 · vdogen.com

Subtitle styling

Caption styling exposes font, size, weight, color, background, opacity, position and rendering modes.Read 15 Oct 2026 · vdogen.com

Supported inputs

The workflow accepts MP4, MOV, MP3 and WAV files for upload and transcription.Read 15 Oct 2026 · vdogen.com

Supported platforms

webRead 21 Sep 2026 · vdogen.com

Talking avatar

A photo and script can be used to generate a lip-synced talking-head video.Read 15 Oct 2026 · vdogen.com

Text-based editing

Users can cut, copy and rearrange transcribed text to reshape the video.Read 15 Oct 2026 · vdogen.com

Transcript editing

Users can delete words, sentences, or blocks from the transcript to recompile the video with smart cuts.Read 11 Oct 2026 · vdogen.com

Transcription

Its automatic captions use Whisper and include word-level timing and speaker detection.Read 11 Oct 2026 · vdogen.com

Translation

The product translates captions into more than 20 languages and supports dual-language captions.Read 15 Oct 2026 · vdogen.com

Video exports

Smart export produces MOV or MP4 with optional burned subtitles and mixed multitrack audio.Read 15 Oct 2026 · vdogen.com

Plans and prices

Every VDOGEN plan and price →

Where Specifiction places it

• Video editors#15 of 718.8
• AI Video Editors#26 of 818.5