FLUX.3
Black Forest Labs' video model. Up to twenty seconds in a single generation with native audio, ten keyframes pinned to exact timecodes, and a draft mode you can render up.
- Start frame
- End frame
- Keyframes
- Audio
- Extend
AI Video Models Supported by Martini
We integrate the industry's leading AI video generators including Veo 3.1, Kling 3.0 Pro, Kling O3 Pro, Sora 2 Pro, and more. Martini is a web-based editor that lets you do everything directly in the browser.
Create cinematic AI-generated shots in our cloud-based timeline, then export as XML to import seamlessly into DaVinci Resolve, Adobe Premiere Pro, or any other editing software.
Many models support start frame control for precise matching with existing shots. End frame control is available with Veo 3.1, Kling 3.0 Pro, Kling O1, Hailuo 02, and Seedance 1.5 for even tighter editorial workflows.
Video Generation Models
These AI models generate video from text prompts or still images, creating motion sequences perfect for professional video production. All models are available directly in the Martini web editor.
Veo 3.1
High-quality video generation with native audio from Google DeepMind. Best for final outputs with start and end frame control.
- Start frame
- End frame
- Audio
Veo 3.1 Fast
Faster variant of Veo 3.1 with native audio. Lower cost with quicker generation times.
- Start frame
- End frame
- Audio
Kling 3.0 Pro
Top-tier video generation with cinematic visuals, fluid motion, native audio, and element support.
- Start frame
- End frame
- Audio
- Elements
- Multi-shot
Kling O3 Pro
Video generation with multi-shot support, extended durations up to 15s, and reference-to-video.
- Start frame
- End frame
- Audio
- Multi-shot
Kling 2.6
Top-tier video generation with cinematic visuals, fluid motion, and native audio support.
- Start frame
- Audio
Kling O1
High-quality image-to-video generation with smooth motion and end frame control.
- Start frame
- End frame
Sora 2 Pro
OpenAI's state-of-the-art video model with native audio, capable of creating richly detailed, dynamic clips from text or images.
- Start frame
- Audio
Sora 2
OpenAI's video model with native audio at 720p. An affordable option for dynamic clips from text or images.
- Start frame
- Audio
MiniMax H3
Multimodal 2K video generation with native stereo audio and image, video, or audio references.
- Start frame
- End frame
- Audio
- Reference media
- 2K
Hailuo 02
MiniMax's advanced video generation model with 1080p resolution and start/end frame control.
- Start frame
- End frame
Seedance 2.5
ByteDance's latest Seedance model, with native 30-second single takes, an Auto duration option, end frame support, and a 50-file reference budget.
- Start frame
- End frame
- Audio
- Reference images
- Elements
- Auto duration
- 30s
Seedance 2.0
ByteDance's most advanced video generation with cinematic output, native audio, real-world physics, and director-level camera control.
- Start frame
- End frame
- Audio
- Reference images
- Elements
- 4K
Seedance 2.0 Fast
Faster, more affordable Seedance 2.0 with cinematic output, native audio, and reference-to-video, capped at 720p for quicker, cheaper generations.
- Start frame
- End frame
- Audio
- Reference images
- Elements
Seedance 2.0 Mini
The quickest, most affordable native Seedance 2.0 tier with audio and reference media, capped at 720p.
- Start frame
- End frame
- Audio
- Reference images
- Elements
Seedance 1.5
High-quality video generation from ByteDance with native audio support and flexible durations from 4-12 seconds.
- Start frame
- End frame
- Audio
Grok Imagine
Video generation from xAI with flexible durations from 1-15 seconds and a wide range of aspect ratios.
- Start frame
Grok Imagine 1.5
Text, image, and reference video generation from xAI with native audio, durations up to 15 seconds, and up to 1080p output.
- Start frame
- References
- Audio
- 1080p
Pixverse V6
High-quality video generation with native audio, flexible durations up to 15 seconds, and art style presets.
- Start frame
- Audio
LTX 2.3
Lightricks' open-source 4K video model with native audio. Supports start/end frame control and durations up to 10 seconds.
- Start frame
- End frame
- Audio
Happy Horse 1.0
Alibaba's #1-ranked video model with native audio, reference-to-video support (up to 9 images), and durations up to 15 seconds.
- Start frame
- Audio
- Reference images
Luma Ray 3.2
Luma's video-to-video model — re-render an existing clip into new cinematic motion from a text prompt, with an optional start frame, at up to 1080p.
- Video to video
- Start frame
Gemini Omni Flash
Google's Gemini Omni Flash — fast text-to-video, image-to-video, and reference-to-video with native synchronized audio and role-bound reference images.
- Start frame
- Reference images
- Elements
- Audio
Still Generation & Image Editing Models
These models specialize in still image generation and editing, perfect for creating reference frames, concept art, or generating motion from static images.
Qwen Image 3.0 Pro
High-fidelity image generation for dense typography, layouts, and precise edits. Add up to three references to preserve identity and details.
- Reference images
- Dense typography
- Precise editing
Grok Imagine Image 2.0
xAI's image model for sharp typography and complex layouts, with photorealistic fidelity across photography, design, and illustration. Add up to three references to edit elements and styles.
- Reference images
- Sharp typography
- Photorealistic fidelity
Reve 2.1
Native 4K image generation with precise layout planning, spatial control, and multilingual text. Add references to edit or remix.
- Reference images
- Native 4K
- Strong text rendering
Nano Banana 2
Fast, affordable image generation with excellent typography and realism. Supports multi-image blending with character consistency.
- Reference images
- Web search
Nano Banana 2 Lite
Google's fastest, most affordable image model. Fixed 1K output with reference-image blending and natural-language editing.
- Reference images
Seedream 5 Lite
ByteDance's fast, affordable image model. High-resolution 2K–4K output with flexible aspect ratios. Add reference images to edit or blend.
- Reference images
- 2K–4K output
Seedream 5 Pro
ByteDance's flagship image model. Sharp high-resolution output with strong text rendering and flexible aspect ratios. Add reference images to edit or blend.
- Reference images
- Strong text rendering
Nano Banana Pro
State-of-the-art image generation with excellent typography and realism. Supports multi-image blending with character consistency.
- Reference images
- Web search
Flux 2 Max
High-quality image generation with flexible aspect ratios and safety controls. Add reference images for creative editing and blending.
- Reference images
GPT Image 2
OpenAI's GPT Image 2 — photoreal image generation with strong typography and instruction following. Add reference images to edit an existing image.
- Reference images
Audio Generation Models
Generate music, sound effects, dialogue, and voiceover. Sonilo SFX can also synchronize foley and ambience to an existing shot. Audio outputs remain editable assets in Martini.
MiniMax Music
Generate complete music tracks from a prompt, with optional vocals and custom lyrics.
- Music
- Instrumental or vocals
- Custom lyrics
MiniMax Music 3
Generate a complete song up to five minutes long, holding theme, vocal identity and arrangement steady across the whole track.
- Music
- Up to 5 minutes
- Custom lyrics
Lyria 3
Generate 30-second music sketches with singing vocals and negative-prompt control.
- Music
- 30 seconds
- Vocals
Lyria 3 Pro
Generate complete songs up to about three minutes with vocals, timed lyrics, and full arrangements.
- Music
- Up to 3 minutes
- Timed lyrics
ElevenLabs Music
Generate vocal or instrumental music from three seconds to ten minutes, with optional section planning.
- Music
- 3 seconds–10 minutes
- Section planning
Stable Audio 2.5
Generate stereo music, foley, and ambient sound design up to 190 seconds.
- Music and SFX
- Up to 190 seconds
- Stereo
Seed Audio 1.0
Generate dialogue, sound effects, and music together from one prompt, or create clean speech.
- Music, SFX, and dialogue
- Up to 2 minutes
- Voice presets
ElevenLabs SFX v2
Generate short foley, ambience, impacts, and atmospheric sounds from text.
- Sound effects
- 0.5–22 seconds
- Text to SFX
Beatoven SFX
Generate stereo effects for creatures, vehicles, impacts, science fiction, and abstract textures.
- Sound effects
- 1–35 seconds
- Stereo
CassetteAI SFX
Generate fast sound-effect placeholders and draft variations up to 30 seconds.
- Sound effects
- 1–30 seconds
- Fast generation
Sonilo SFX
Generate standalone sound effects from text, or add a source video for frame-synchronized foley and ambience.
- Text to sound effects
- Video synchronization
- 1–180 seconds
- AAC, MP3, WAV, FLAC
ElevenLabs TTS v3
Generate expressive dialogue and voiceover with preset voices, language control, and delivery tags.
- Dialogue and voiceover
- 21 voices
- 70+ languages
MiniMax Speech-02 HD
Generate natural narration and character dialogue with broad voice and language support.
- Dialogue and voiceover
- 17 voices
- 40+ languages
Frequently Asked Questions
Yes. Martini is a web-based editor that lets you generate Veo 3 shots directly in the browser. You can then export your project as XML and import it seamlessly into Adobe Premiere Pro, DaVinci Resolve, or any other editing software.
Yes. Kling 3.0 Pro, Kling O3 Pro, and Kling O1 all support start and end frame control, enabling tight in/out precision for editorial workflows. This allows you to match your AI-generated content exactly to your existing shots for seamless continuity.
Martini supports leading AI video generation models including Veo 3.1, Kling 3.0 Pro, Kling O3 Pro, Kling 2.6, Kling O1, Sora 2 Pro, Hailuo 02, Seedance 1.5, and Grok Imagine. For still image generation and editing, we support Nano Banana Pro and Flux 2 Max. All models are available directly in the Martini web editor, allowing you to choose the best model for each shot in a single unified interface.
Yes. Martini supports Nano Banana Pro for high-quality image generation with excellent typography and multi-image blending, and Flux 2 Max for flexible aspect ratios and creative editing with reference images. Generate reference frames directly in your timeline.
For music, Martini supports MiniMax Music, Lyria 3, Lyria 3 Pro, ElevenLabs Music, and Stable Audio 2.5. Sound-effect models include ElevenLabs SFX v2, Beatoven SFX, CassetteAI SFX, Sonilo SFX, and Stable Audio 2.5. Dialogue and voiceover models include ElevenLabs TTS v3 and MiniMax Speech-02 HD. Seed Audio 1.0 can generate music, sound effects, and dialogue together.
Martini works with any professional video editor that supports XML import, including Adobe Premiere Pro and DaVinci Resolve. Simply create in our web editor and export your timeline to XML. This gives you the flexibility of a cloud-based AI studio with the power of your preferred desktop NLE.
Yes. End frame control is available with Veo 3.1, Kling 3.0 Pro, Kling O3 Pro, Kling O1, Hailuo 02, and Seedance 1.5, giving you precise control over both the start and end frames of your AI-generated videos for tighter editorial workflows. This feature is essential for matching existing shots and maintaining continuity in professional productions.
Martini combines a professional timeline interface with AI generation in the browser. Instead of managing scattered video files, you build your sequence in our web editor and export to XML, seamlessly bridging the gap between AI generation and professional post-production.
Yes. We offer a creative partnership program for studios, agencies, and independent creators working on notable projects. Partners receive priority support, early access to new features, collaborative opportunities, and custom integrations. Contact us at koh@c47.studio to learn more about partnership opportunities.
Ready to get started?
For creatives, studios, and agencies who create professional AI videos.