CAST

Settings

AI Provider

Provider Model

API Key

Story Length

Story Prompt

The writing-style rules sent to the AI for every story. Edit to change tone, structure, or content rules.

Video Output

Width

Height

FPS

Default Music Volume 25%

Starting background-music volume for the sidebar's own slider and every new batch card. Still adjustable per video afterward.

Caption Style

Preset

Font

Font Size

Position Y

Text Color

Stroke Color

Stroke Width

Narration Voice

TTS Engine

Voice

Improve caption sync with AI transcription (slower, ~40MB download)

Only used when a local native Whisper backend isn't already available (that's used automatically and is faster) — this runs speech-to-text in your browser instead to get real word timestamps, rather than an estimate.

Title Card Identity

Used when a video has the title card enabled. The title card itself is turned on per-video.

Channel Name Profile Picture

Appearance

Theme Accent Color Compact layout Reduce motion UI Text Size 100%

Settings Backup

Debug

Check how captions/title card actually look without generating a full story or waiting on TTS.

Sample caption text Also test TTS generation (uses the selected engine/voice above)

AITAH story videos — runs 100% in your browser

⚠️ This is the legacy zero-install web version, kept around for the "click a link, no install" case. It's no longer where active development happens — the actively developed version now runs as a local app with native rendering/transcription instead of in-browser WASM. Some newer features may not be here yet.

Everything runs locally: TTS uses Piper (in-browser), video renders with ffmpeg.wasm. First use downloads the voice model + engine once.

1Background Video

🎬

Click to upload background video

2Story

Premise / Idea

Story Text

3Preview & Export

Title card

Background Music

No music selected.

Music Volume

Preview plays captions in real-time. Export renders the MP4.

Upload a background video

Downloading TTS model...