Help & Reference
What every option does, where your files go, and how ImTalking handles your data.
Processing Options Explained
How many video frames are rendered at once. Higher = faster, but uses more RAM. The default of 2 is safe for most systems.
Upscales the output to a higher resolution after rendering, adding clarity without re-rendering. Most useful when Enhance is off.
Controls how expressive the lip and face movement is. 1.0 is natural; 1.2–1.5 gives more dramatic expressions.
Applies GFPGAN face restoration to every frame for a noticeably sharper result. Adds processing time.
Keeps the head stable with minimal random movement — ideal for presentation-style videos.
Pause Behaviour Between Sentences
ImTalking automatically inserts still-frame pauses between sentences based on punctuation:
- Period, question mark, exclamation mark → 1.0 second still pause
- Comma, dash → 0.5 second still pause
Accessing Your Video Library
Every video you generate is saved automatically and listed in the Projects tab inside the app, along with the settings used to create it. Click Refresh there to load your history, or use Open Folder after any generation to jump straight to the file on disk.
Generated videos are saved locally to C:\Users\[you]\Videos\SadTalker\ and never uploaded anywhere.
Privacy & Data
- Imported photos are stored in the app's local library folder.
- Generated speech audio is saved temporarily and deleted after the video is created.
- Face data is extracted on-device using SadTalker's 3D facial model and discarded immediately after generation — nothing biometric is stored or transmitted.
- The only network activity is downloading TTS voices via Microsoft Edge TTS and checking for certificate updates for the local connection — no analytics, no telemetry.