The AI models behind Clip AI
Clip AI picks the right engines for every story: Google Veo 3.1 for video with native dialogue audio, Gemini (Nano Banana) and GPT Image 2 for posters and stills, Kling 3.0 and the Kling Omni models, Runway Gen-4.5, Seedance 2.0 and LTX 2.3 for motion, Claude for the script and ElevenLabs for voice and music. You never have to choose one.
Video models
Image-to-video and text-to-video engines that animate every scene.
- Google Veo 3.1 (Flow) · video + native audio
- Motion 2.0 Fast
- Motion 2.0 Quality
- Kling 2.5 Turbo
- Kling 2.6
- Kling 3.0
- Kling 2.1 Pro
- Seedance 2.0
- Seedance 2.0 Fast
- Runway Gen-4 Turbo
- Runway Gen-4.5
- LTX 2.3 Pro
- LTX 2.3 Fast
- Kling O1 · Omni
- Kling O3 · Omni
- Veo3.1 Fast
- Veo3.1 Quality
Image models
Posters, title cards and start frames, including Google Gemini image models.
- Gemini image (Nano Banana) · Google
- Phoenix 1.0
- Lucid Origin
- Lucid Realism
- Kino XL
- AlbedoBase XL
- Leonardo Diffusion XL
- Leonardo Vision XL
- Nano Banana
- Nano Banana 2 Lite
- GPT Image 2
- Seedream 4.5
- Nano Banana Pro
- Nano Banana 2
- Seedream 5.0 Pro
- FLUX.2 Pro
- Seedream 4.0
Story & script models
Large language models that write the script, dialogue and scene prompts.
- Claude Haiku 4.5 · Anthropic
- Claude Sonnet 4.5 · Anthropic
- Claude Sonnet 4 · Anthropic
- ChatGPT-4o · OpenAI
- ChatGPT-4o Mini · OpenAI
- Gemini 2.0 Flash · Google
- Gemini 2.5 Flash · Google
Voice, dialogue & music
Spoken dialogue, narration and the soundtrack.
- ElevenLabs voices · narration
- ElevenLabs Music · soundtrack
- Veo 3.1 native dialogue audio · lip-synced speech