The modelsThe available models
Gemini Omni
Text and image references, 4 to 10 seconds, in 720p or 1080p.
Gemini Omni 1.1
Characters who speak in one of 30 Gemini voices, with native lip-sync. Text or up to 7 images, 4 to 10 seconds.
Seedance 2.5
Best for cinematic and advertising stories up to 30 seconds, with precise control over references, motion, and editing.
Seedance 2.0
Three modes: text, keyframe, and references.
Grok Video
Video generation in 6, 10, or 15-second formats.
Veo
Three rendering levels: Lite, Fast, and Quality.
HappyHorse
Text, image, multi-reference, and video editing.
Kling 3.0
Multi-shot, persistent elements, and control frames.
Motion Control
Motion transfer from a reference video.
Kling 2.6
Advanced motion and generation with sound.
EcoGen 1
Create 5–15 second videos with sound from text, a first frame, or image, video and audio references.
Nano Banana 2 Lite
Fast generation and editing with up to 10 references, in 1K.
GPT Image 2.5 Sunburst
The most polished: posters, brand visuals and campaign-ready product images with crisp text, up to 4K.
GPT Image 2.5 Flare
Fast: social visuals, everyday creations and edits with crisp text, up to 4K.
GPT Image 2
Best for infographics, graphic design, complex visual compositions, and text-rich images, up to 4K.
Nano Banana 2
Best for fast, precise photo retouching, subject preservation, and reference-guided edits, up to 4K.
Nano Banana Pro
Best for high-fidelity photo retouching, precise local edits, and subject consistency across multiple references, up to 4K.
Grok Image
Generation or editing from one reference.
Z-Image
Simple, affordable text-to-image generation.
Seedream v5.0 Lite
Generation and editing with up to ten reference images.
Seedream v5.0 Lite Sequential
A consistent sequence generated or edited with references.
Open TTS
Natural multilingual voices with a narrator catalogue and personal voices.
ElevenLabs v4
Voice-overs, audiobooks and narration in more than 80 languages, directed with tags such as [whispers] or [laughs].
ElevenLabs v4 Turbo
The fast version of ElevenLabs v4: the same voices and languages at a lower cost.
Gemini Flash TTS
Expressive, natural voices with optimized cost.
MiniMax Speech 2.6 HD
HD voices with support for authorized personal voices.
Deepnia Long-form
Turn long text, PDFs, Word documents, and PowerPoint presentations into one MP3.