All models

MiniMax H3: multimodal 2K video with native stereo audio. Text-to-video, image-to-video (first + last frame), and reference-to-video (up to 9 images / 3 clips / 3 audio refs).

Flux 3: native-audio video with first/last frame control, up to 20s and 1080p.

Hailuo-02 Pro video generation

Kandinsky 5.0 Pro video generation

Grok Imagine video generation

Wan 2.2 5B with fewer restrictions

Hunyuan video generation

Luma Dream Machine Ray 2 video generation

Magi video generation

LTX-2 19B Distilled high-quality video generation

Fast LTX 2.3 video generation with audio, up to 4K and 20s duration

High-fidelity LTX 2.3 Pro video generation with audio, up to 4K and 48fps

High-quality video upscaling. Optional FPS boost up to 120, plus fine-grained denoise / halo / grain controls and per-variant enhancement models (Proteus, Starlight, Artemis, Nyx, Gaia).

Diffusion-based video upscaler with temporal consistency. Supports factor-based or target-resolution upscaling, plus output format/quality controls.

Automatically remove the background from a video — no green screen required. Replace it with a solid color or keep transparency for compositing. Works best on clips under 30 seconds.

Automatically cut filler words ("um", "uh", "you know") and overlong silences out of a finished talking video. The result is a tighter re-cut of the same footage — no re-shoot, no re-render, and the original audio and framing are preserved between cuts.

Replace the spoken voice in a talking video with a cloned voice — an influencer's voice (influencer_id) or any voice the team owns (voice_id, e.g. created via /api/v2/voice-clone) — while preserving the original lip-sync, timing, and background audio. Ideal for unifying narration across clips without re-shooting or re-rendering.

Precision-focused lip-sync with high-fidelity mouth movement and facial preservation.

Production-focused lip-sync that works for multiple angles and languages.

High-quality video with premium AI lip-sync

Kling 3 Pro talking head with AI voice conversion. Cinematic video driven by an image + script (native audio).

Kling 3 Pro talking head from an uploaded video reference. Re-generates the clip with AI voice conversion.

Studio-quality talking head with premium lip-sync

Expressive talking avatar with natural lip movements

OmniHuman v1.5 talking head. Vivid emotions and movements correlated with the input audio.

Expressive performance with natural speech coordination

Recreate a public TikTok or Instagram video with your own influencer performing it. Admin only for now.

WAN 2.2 14B with custom LoRA weights. Pass high-noise + low-noise variants together for best results.

Generate 3D models from text or an image. Supports preview/full modes, art styles, and PBR textures.

Automatically rig a humanoid 3D model (GLB) with a skeleton and smooth skin weights. Returns a poseable rigged GLB (plus basic walking/running animations) in 1–3 minutes.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.

Generate text. Supports temperature, max_tokens, and system_prompt.