Supported Models

Google AI Studio

State-of-the-art video generation with audio. Text-to-video and image-to-video.

Google AI Studio

Faster inference variant of Veo 3.1 for rapid iteration.

OpenAI

High-quality video generation from text and image inputs.

OpenAI

Premium video generation with higher resolution and longer durations.

fal.ai

High-quality video generation with strong motion consistency.

fal.ai

Dance and motion-focused video generation with natural movement.

fal.ai

Text-to-video with strong character consistency. 14B parameter model.

fal.ai

Latest Wan model with improved quality and longer durations.

fal.ai

Tencent's 13B parameter video generation model via fal.ai.

Google AI Studio

High-quality image generation with excellent prompt adherence.

Google AI Studio

Next-gen image generation with improved detail and consistency.

Black Forest Labs

High-quality image generation with excellent prompt adherence and detail.

Local (Sidecar)

Lightweight FLUX model for local image generation on Mac (Metal/MPS).

Google AI Studio

Advanced reasoning and multimodal understanding with 1M token context.

Google AI Studio

Fast, cost-efficient model for everyday tasks. 1M context.

OpenAI

Advanced LLM with strong reasoning and 128K context window.

Anthropic

High-capability model with excellent instruction following and 200K context.

Local (Ollama)

Compact LLM for script writing and AI assistant. Runs fully on-device.

ElevenLabs

High-quality multilingual voice cloning and text-to-speech.

ElevenLabs

Low-latency voice synthesis for fast iteration and previews.

Google AI Studio

Cloud-based transcription via Gemini with high accuracy.

OpenAI

Cloud-based transcription via OpenAI with word-level timestamps.

ElevenLabs

ElevenLabs transcription with speaker detection.

Local (bundled)

Lightweight on-device transcription. Bundled with Skia, no download required.

Local (download)

Higher-accuracy on-device transcription. One-time download (~500 MB).