Powered by the world's strongest AI. Depth Studio unifies the latest
models from industry-leading AI providers under one roof, so a production team can pick the
right engine for each shot without leaving the workspace.
Video generation models
Cinematic quality, high-consistency and professional video synthesis tools.
Veo — Google's highest quality cinematic video generation architecture.
Kling — top-tier generation with motion control and lip sync; Kling 4.0 animates from reference images, videos, elements and voices or between first, in-between and last keyframes (up to 30 s); Kling O3 adds text, frame and reference modes in one model, native audio, 4K and six-shot planning.
Runway — industry-standard cinematic realism, including video-to-video restyling.
Seedance — multimodal video generation with lip sync and multi-scene consistency.
Wan — production-grade video synthesis with fast, cost-efficient modes; Wan 3.0 Video and Wan 3.0 Video Prime accept first and last frames plus up to ten reference images and five reference clips.
Gemini Omni 1.1 Flash — Google's fast Omni tier: 360p to 4K, four to ten seconds, and editing of a clip you supply.
Hailuo — creative and dynamic movement generation.
MiniMax H3 — 2K video from text, first/last frames or reference media, with native audio.
PixVerse V6 — text and image to video with transitions, extension and reference mode, 360p to 1080p with audio.
Grok Imagine Video 1.5 — xAI's video model, 480p to 1080p, one to fifteen seconds.
OmniHuman 1.5 and Kling AI Avatar — talking, moving people from a single image and an audio track.
Topaz Video Upscaler — enhancement and upscaling of finished clips.
Image generation models
Visual creation ranging from artistic excellence to technical photorealism.
GPT Image 2.5 — OpenAI's image model, 1K to 4K, from text or reference images.
Imagen — flawless photorealism with Google's latest architecture.
Flux — world-class detail, composition and prompt adherence.
Seedream — ByteDance's high-fidelity image models with strong complex-scene handling.
Ideogram — high-end typography, graphic design and character consistency.
Nano Banana — optimised engine for fast, creative visual production.
Qwen Image — advanced editing and image generation; Qwen Image 3.0 adds 1K/2K output, negative prompts and up to three reference images.
Grok Imagine Image 2.0 — xAI's image model, from text or from up to five reference images.
Topaz Image Upscaler — image upscaling and enhancement.
Audio and music models
Unique music compositions and realistic voice synthesis technologies.
Suno — full song generation with music and vocals.
ElevenLabs — the most realistic AI voices and sound effects, multilingual including Turkish.
SFX engine and audio isolation — cinematic sound generation, noise removal and voice separation.
Large language models (LLM)
The most advanced intelligences for complex reasoning, coding and creative writing —
used inside Depth Studio for script analysis, scene breakdown and prompt building.
Gemini — multi-modal intelligence with a large context window, from the fast Flash tiers (up to Gemini 3.8 Flash) to Gemini 3.1 Pro.
GPT series — advanced reasoning, planning and multi-step thinking, from the three GPT-5.6 tiers (Luna, Terra, Sol) up to GPT-6 Astra.
Claude — long document analysis and safe AI processing, up to Claude Opus 5.
Grok — xAI's chat models, up to Grok 4.7, with adjustable reasoning and web search.
Kimi K3 — Moonshot AI's model with a one-million-token context window.
DeepSeek V4.1 Flash — the most economical chat model for fast text work.