Tools and pricing

The agent that builds your video — it plans, writes, and edits every scene from a prompt. Billed per token across three tiers.

Watermark-free HD export of your finished video. Any one-time balance top-up (from $9) unlocks it — no subscription required.

Unlock the complete Claude Code and Codex prompt for every current and future Baz video skill — a yearly subscription that always stays up to date.

Cinematic clips with native audio and remarkable physical realism.

Flagship image-to-video with strong motion and camera control.

Reliable previous-generation image-to-video at a lower cost.

Lifelike AI presenters that speak your script to camera.

Generate or edit images with AI — the default image engine.

High-quality image generation, up to 8 reference images.

Legacy AI image generation.

One-click AI background removal for any image.

Premium, expressive voice synthesis — the industry standard for voice cloning and lifelike narration. Use it out of the box, or connect your own ElevenLabs account to bring everything with you.

Fast, affordable text-to-speech with a huge multilingual voice library — ideal for high-volume narration where cost and speed matter.

Low-latency, natural text-to-speech from Gemini Flash. Its standout trick: describe the voice you want in plain English — accent, character, mood, pacing — and it delivers. It follows voice descriptions unusually well.

AI music generation for background beds.

Full-length AI songs, up to 8 minutes.

Extract and download images from any webpage.

Pull brand colours, fonts, and style from any URL.

Analyse images for descriptions, categorisation, or comparison.

Static map images generated from coordinates.