vEdition — User Guide

Version 2.7 · April 2026

What is vEdition?

vEdition is a desktop application for creating professional tutorial videos from screen recordings. It captures user actions (clicks, keystrokes, drag, scroll, text input), structures them into tutorial steps, generates narration scripts and voice tracks using AI, and exports polished assets in multiple formats.

Two applications:

Component	Purpose	Price
Recorder	Records screen + user actions	Free
Studio	AI narration, voice, timeline editing, export	€99 (Pro) / €249 (Team)

Who is it for: freelance tutors, online course creators, educators, product teams, onboarding specialists, IT trainers, and training studios.

Requirements

Windows 10/11 (x64)
FFmpeg (for recording and audio processing)
Recorder is a standalone app (bundled JVM runtime)
JDK 21 runtime bundled in Studio MSI

Installing FFmpeg

winget install Gyan.FFmpeg

Or: choco install ffmpeg / download from ffmpeg.org.

Studio checks for FFmpeg on launch. If not found, a red banner appears with a one-click Install FFmpeg button (uses winget).

AI Setup

On first launch, Studio shows a setup wizard with five options. You can change your choice anytime via the AI: … button in the toolbar.

Tier	LLM (narration text)	TTS (voice)	API key	Cost
OpenAI	GPT-4o-mini	OpenAI TTS-1	Required	~$0.05–0.15/session
Custom LLM	DeepSeek, Groq, Together, etc.	Any (choose separately)	Depends	Varies
Free Cloud	Ollama (local)	Edge TTS (free Microsoft)	No	Free
Fully Offline	Ollama (local)	Piper TTS (local)	No	Free
Manual	—	—	No	Free

OpenAI setup

Go to platform.openai.com/api-keys
Create new secret key (starts with sk-...)
Go to Settings → Billing → add a payment method (minimum $5)
Paste the key in the wizard → click Validate Key

Custom LLM setup

Use any OpenAI-compatible API. The wizard offers quick presets:

Provider	Base URL	Signup
DeepSeek	https://api.deepseek.com	platform.deepseek.com
Groq	https://api.groq.com/openai	console.groq.com
Together AI	https://api.together.xyz	api.together.xyz
Fireworks AI	https://api.fireworks.ai/inference	fireworks.ai
OpenRouter	https://openrouter.ai/api	openrouter.ai
LM Studio (local)	http://localhost:1234	lmstudio.ai

You can mix any LLM with any TTS provider. For example: DeepSeek for narration + ElevenLabs for voice.

Voice providers

Provider	Quality	Key	Cost
OpenAI TTS-1	Excellent	Required	~$0.015/1K chars
ElevenLabs	Excellent	Required	Free tier + paid plans
Edge TTS (Microsoft)	Very good	None	Free
Piper TTS	Good (offline)	None	Free, ~75 MB/voice

Ollama setup (for Free Cloud and Offline tiers)

Install: winget install Ollama.Ollama or ollama.com
Pull a model: ollama pull llama3.2 (~2 GB download)
Ollama runs as a local server on port 11434

Recommended models: llama3.2 (best balance), phi3:mini (fast), gemma2:2b (fastest), mistral (best quality, slower).

Piper TTS setup (for Offline tier)

Studio downloads Piper binary and voice models automatically. Stored in %APPDATA%\vEdition\piper\. Available voices: English (US, GB), German, Russian, French, Spanish.

Part 1: Recording

Run vEdition Recorder (free, no license needed).

Capture modes

Mode	How to select	Description
Full screen	Default	Records entire selected monitor
Region	Click Region button	Drag to select rectangle (min 100×100)
Window	Click Window button	Hover → green border → click to select

Recording process

Choose output folder (default: Documents\vEdition Sessions)
Select monitor and capture mode
Click Record
Perform your tutorial actions
Click Stop (floating button, top-right) or press the stop hotkey (default: F9, configurable)

What gets captured

Action	Detection
Left click	LMB release (after checking for drag)
Right click	RMB press
Double click	Two clicks within 400ms / 8px
Drag	LMB held + movement > 10px
Key combos	Ctrl/Alt/Shift + key
Text input	Consecutive characters (aggregated)
Special keys	Enter, Escape, Tab, F1–F12
Scroll	Mouse wheel (batched within 500ms)

Session output

session_20260403_143022/
│── capture.mp4           ← screen video
│── actions.json          ← action log
└── session.meta.json     ← metadata

Part 2: Editing (Studio)

Run vEdition Studio (requires license after 7-day trial).

Toolbar

Button	Action
Open Session	Open a recorded session folder
Undo	Undo last change (Ctrl+Z, 50 levels)
AI All	Generate narration for all steps
Voice All	Generate voice for all steps with narration
Voice / Lang	Select voice and language
Key + Validate	OpenAI API key (with ✓ validation button)
AI: …	Current AI tier (click to change)
Render	Render to MP4, WebM, ProRes, GIF, WAV
Export	Export to VEGAS, EDL, SRT, Markdown
License	License management (enter/replace/deactivate/remove key)

Timeline — 4 tracks

Track	Content	Color
Ruler	Time scale with major/minor ticks	Dark
Events	Action markers (colored by type)	Colored dots
Video	Video step regions (numbered blocks)	Blue
Audio	Waveform blocks or placeholders	Green / gray dashed

Timeline interactions

Action	What happens
Click	Seek video + select step
Drag on empty area	Create render region (yellow bar)
Mouse wheel	Zoom in/out (1x–20x)
Shift + wheel	Horizontal scroll
Drag audio block body	Move audio offset
Drag purple triangle (left)	Fit — stretch/compress audio
Drag green triangle (right)	Trim audio from end
Drag render region edges	Resize render region
Right click	Context menu (add step, fit, volume, delete)

Step details (right panel)

Button	Description
AI	Generate narration for this step
Voice	Generate voice from narration text
Play	Play audio for this step
Delete Audio	Remove audio file
Delete Step	Remove step entirely
Export WAV	Save audio to file

Audio operations

Fit (purple triangle): Stretch or compress audio to match video duration. Always works from the original file — no quality loss on repeated fits.
Trim (green triangle): Cut audio from the right edge. Uses FFmpeg -t on original.
Move (drag body): Shift audio offset relative to step start.
Volume (right click): Adjust volume in dB (-20 to +20). Applied via FFmpeg.

Part 3: Workflow

Step 1: Record

Launch Recorder → choose capture mode → Record
Perform tutorial actions → Stop

Step 2: Edit in Studio

Open Session → select session folder
Steps auto-detected from action pauses (>1.5s gaps)
Edit narration text or click AI / AI All
Click Voice / Voice All to generate audio

Step 3: Adjust

Fit, trim, move audio blocks to match video timing
Adjust volume per step or per region
Add or delete steps via right-click context menu

Step 4: Export

Set render region (drag on timeline) then use Render or Export menu.

Export Formats

Format	Type	Use case
MP4 (H.264)	Video	Web delivery, general use
WebM (VP9)	Video	Web embedding, HTML5
ProRes MOV	Video	Professional post-production
GIF	Video	Quick previews, documentation
WAV	Audio	Audio-only export
SRT	Subtitles	YouTube, Vimeo, LMS
EDL (CMX 3600)	Timeline	DaVinci Resolve, Premiere Pro
VEGAS .cs	Script	VEGAS Pro import
Markdown	Text	Written tutorial, documentation

Licensing

Product	Price	Activations
Recorder	Free	Unlimited
Studio Pro	€99	1 device
Studio Team	€249	3 devices

Trial

7-day free trial with full functionality, no credit card
All AI tiers available during trial (including free options)
Trial counter stored locally — starts on first Studio launch

License key lifecycle

Action	How	What happens
Purchase	vedition.pro → Buy Pro/Team	Key emailed instantly via Lemon Squeezy
Enter key	First launch or 🔑 button → License Manager	Key field + Activate button
Test format	License Manager → Test Format	Checks key format before activating
Activate	License Manager → Activate	Binds key to machine (HWID), validates with Lemon Squeezy API
Replace key	License Manager → enter new key → Replace & Activate	Deactivates old key, activates new one
Deactivate	License Manager → Deactivate License	Frees seat for another device, key remains valid
Remove data	License Manager → Remove License Data	Deletes local license file, resets to trial state

Offline & validation

License validated online at each launch (quick GET request)
If offline: works for up to 30 days from last successful validation
After 30 days offline: requires internet to re-validate
License stored encrypted in %APPDATA%\vEdition\license.dat

Configuration

Location: %APPDATA%\vEdition\config.env

Key	Description	Default
AI_TIER	AI mode: OPENAI, CUSTOM_LLM, FREE_CLOUD, OFFLINE, MANUAL	MANUAL
OPENAI_API_KEY	OpenAI API key	(empty)
CUSTOM_LLM_URL	Custom LLM base URL	(empty)
CUSTOM_LLM_KEY	Custom LLM API key	(empty)
CUSTOM_LLM_MODEL	Custom LLM model name	(empty)
OLLAMA_MODEL	Ollama model	llama3.2
TTS_PROVIDER	OPENAI, EDGE, ELEVENLABS, PIPER, NONE	OPENAI
TTS_VOICE	Voice name	alloy
TTS_LANGUAGE	Language code	en
ELEVENLABS_KEY	ElevenLabs API key	(empty)
SESSIONS_DIR	Session save folder	Documents\vEdition Sessions

Audio & Waveforms

Green blocks with waveform = audio exists
Gray dashed blocks = audio not generated
Block width = real audio duration
Purple triangle (left) = fit handle
Green triangle (right) = trim handle

Original file principle: audioOriginalPath stores the untouched TTS file. All operations (fit/trim/volume) read from the original and write to a new timestamped file. No quality degradation on repeated edits.

FAQ

Recording

capture.mp4 is empty / 0 bytes
FFmpeg didn’t start. Run ffmpeg -version in a terminal to verify it’s installed.

Clicks from other monitors are recorded
Select the correct monitor in the dropdown before recording.

Studio

“Configure AI in Settings”
Click the AI: … button in the toolbar to run the setup wizard.

Fit produces wrong duration
Fit uses the render region if selected. Drag-select the desired range on the timeline first, then fit.

FFmpeg not found banner
Click Install FFmpeg or run winget install Gyan.FFmpeg in a terminal.

AI & Voice

“API key error: Invalid API key”
Check at platform.openai.com/api-keys. Make sure billing is enabled.

“Ollama error”
Make sure Ollama is running: ollama serve. Verify model is downloaded: ollama list.

Edge TTS not working
Install via pip install edge-tts. Requires internet connection.

Can I mix providers?
Yes. Choose Custom LLM tier, then select any LLM + any TTS independently. Example: DeepSeek for text + ElevenLabs for voice.

Licensing

How do I move my license to another computer?
Click 🔑 in toolbar → License Manager → Deactivate License. This frees the seat. Install Studio on the new machine and enter the same key.

How do I replace my license key?
Click 🔑 → License Manager → enter new key → Replace & Activate. Old key is deactivated automatically.

Trial expired but I haven’t bought yet
Recorder still works (it’s free). Studio requires a license key after 7 days. You can still use all free AI tiers during trial.

Team license — how do 3 seats work?
One key, up to 3 activations on different machines. Each person activates with the same key. Deactivate from one machine to free a seat.

AI Pricing

Provider	Task	Cost per session (10–20 steps)
OpenAI (GPT-4o-mini + TTS-1)	Narration + voice	~$0.05–0.15
DeepSeek	Narration	~$0.01–0.03
Groq (free tier)	Narration	Free (rate limited)
ElevenLabs (free tier)	Voice	Free (10K chars/month)
Edge TTS	Voice	Free
Ollama + Piper	Narration + voice	Free (local CPU)

Session File Structure

session_20260403_143022/
│── capture.mp4               ← screen recording
│── actions.json              ← action log
│── session.meta.json         ← metadata
│── session.tflow             ← auto-saved state
│── import_to_vegas.cs        ← VEGAS script
│── tutorial.srt              ← subtitles
│── tutorial.md               ← markdown
│── tutorial.edl              ← EDL timeline
│── audio/
│   │── step_1.wav            ← original TTS
│   │── step_1_fit_17128.wav  ← stretched
│   └── step_2.wav

Supported Voices

OpenAI TTS

Voice	Character
alloy	Neutral (default)
echo	Warm
fable	Narrative
onyx	Deep
nova	Bright
shimmer	Crisp

Edge TTS (selected)

Language	Voice
English (US)	GuyNeural, JennyNeural, AriaNeural
Russian	DmitryNeural, SvetlanaNeural
German	ConradNeural, KatjaNeural
French	HenriNeural, DeniseNeural
Spanish	AlvaroNeural, ElviraNeural
Japanese	KeitaNeural, NanamiNeural

ElevenLabs (default voices)

Voice	Character
Rachel	Calm, narration
Antoni	Well-rounded, male
Adam	Deep, narration
Josh	Deep, male
Bella	Soft, warm
Sam	Raspy, male

Supported AI Providers

LLM (narration text)

Provider	Type	Key required
OpenAI	Cloud	Yes
DeepSeek	Cloud	Yes
Groq	Cloud	Yes (free tier)
Together AI	Cloud	Yes
Fireworks AI	Cloud	Yes
OpenRouter	Cloud	Yes
LM Studio	Local	No
Ollama	Local	No
Any OpenAI-compatible	Custom URL	Optional

TTS (voice generation)

Provider	Type	Key required
OpenAI TTS-1	Cloud	Yes
ElevenLabs	Cloud	Yes
Edge TTS (Microsoft)	Cloud (free)	No
Piper	Local	No