Model catalog · 48 models

Every leading AI model. One subscription.

Pick the best model for each shot — or let Autopilot choose for you. New models are added the day they launch.

Video

Text-to-video and image-to-video, many with native sound.

16 models

  • Veo 3.1

    Google DeepMind

    Top pickAudio4K

    Top-tier cinematic realism with native synchronized audio, dialogue and sound effects.

    Try it
  • Veo 3.1 Fast

    Google DeepMind

    FastAudio

    Veo quality at a fraction of the price and wait — great for iterating.

    Try it
  • Veo 3.1 Lite

    Google DeepMind

    Best valueAudio

    The most affordable way to get Veo realism with sound — perfect for drafts and social.

    Try it
  • Kling 3.0 Pro

    Kuaishou

    Top pickAudioNew

    Outstanding motion and camera control, up to 15s, with native audio.

    Try it
  • Kling 3.0 Turbo

    Kuaishou

    Fast

    Kling quality, faster turnaround. Great all-rounder.

    Try it
  • Seedance 2.5

    ByteDance

    NewAudio

    Multi-shot storytelling up to 30s with native audio and crisp 1080p.

    Try it
  • Seedance 2.0 Fast

    ByteDance

    FastAudio

    Fast, smooth, stable motion — ideal for product shots and social clips.

    Try it
  • MiniMax H3 Max

    MiniMax

    NewBest value

    Excellent physics and human motion up to 15s. Superb value.

    Try it
  • Wan 3.0

    Alibaba

    AudioBest value

    Up to 30s clips with native audio and strong multilingual prompt understanding.

    Try it
  • Gemini Omni Flash

    Google

    NewFast

    Fast, versatile video from Gemini — from quick 360p drafts to 4K.

    Try it
  • FLUX 3 Video

    Black Forest Labs

    NewAudio

    Photographic realism and beautiful lighting with native audio.

    Try it
  • Ray 3.2

    Luma AI

    Dreamy, cinematic camera moves with natural light and optional HDR.

    Try it
  • PixVerse V6

    PixVerse

    FastBest value

    Fast, stylish clips with anime, 3D and clay styles — great for social content.

    Try it
  • Grok Imagine Video

    xAI

    Punchy, expressive clips with bold motion and wide aspect-ratio support.

    Try it
  • LTX 2.5 Pro

    Lightricks

    Audio

    Director-style camera moves (dolly, jib, focus shift) at up to 50fps.

    Try it
  • Vidu Q3

    Shengshu

    Audio

    Anime and stylised motion specialist with native audio.

    Try it

Image

Photoreal images, product shots, design and text rendering.

10 models

  • Nano Banana Pro

    Google

    Top pick4K

    Gemini 3 Pro Image — best-in-class editing, character consistency and text rendering, up to 4K.

    Try it
  • Nano Banana 2

    Google

    Fast

    Fast Gemini image generation & editing with great prompt adherence.

    Try it
  • GPT Image 2

    OpenAI

    Top pick

    Superb instruction following, text and layouts; transparent backgrounds.

    Try it
  • Seedream 5.0 Pro

    ByteDance

    Ultra-sharp images for products, posters and edits with multi-image references.

    Try it
  • Seedream 5.0 Lite

    ByteDance

    Best value

    Great quality at a low price — ideal for storyboards and keyframes.

    Try it
  • FLUX.2 [pro]

    Black Forest Labs

    Natural, high-fidelity photography with superb composition and editing.

    Try it
  • FLUX.1 Kontext [pro]

    Black Forest Labs

    Edit any image with words — change style, objects, text or background.

    Try it
  • Ideogram V4

    Ideogram

    The best model for typography, logos, posters and graphic design.

    Try it
  • Recraft V4.1

    Recraft

    Design-grade illustrations, icons and brand-consistent visuals.

    Try it
  • Qwen Image 3

    Alibaba

    Strong multilingual text rendering (incl. Arabic & Chinese) and precise edits.

    Try it

Voice

Lifelike speech and narration in dozens of languages.

5 models

  • Eleven v3

    ElevenLabs

    Top pick

    The most expressive text-to-speech — emotions, whispers, laughter. 70+ languages.

    Try it
  • Multilingual v2

    ElevenLabs

    Stable, lifelike narration in 29 languages — perfect for long voiceovers.

    Try it
  • Gemini 3.1 Flash TTS

    Google

    NewBest value

    Natural voices with style direction, multi-speaker dialogue, native Arabic dialects.

    Try it
  • Speech 2.8 HD

    MiniMax

    High-fidelity speech in 40+ languages with emotion control.

    Try it
  • Grok Voice

    xAI

    Best value

    Very affordable, natural voices with Egyptian, Saudi and Emirati Arabic.

    Try it

Music

Original, royalty-free songs, scores and loops.

4 models

  • Lyria 3.5

    Google DeepMind

    Top pickNew

    High-fidelity music across genres, with or without lyrics.

    Try it
  • Eleven Music

    ElevenLabs

    Full songs with vocals or instrumentals, licensed for commercial use.

    Try it
  • MiniMax Music 2.6

    MiniMax

    Catchy full tracks with auto-written lyrics or pure instrumentals.

    Try it
  • Stable Audio 3

    Stability AI

    Best valueFast

    Loops, beats and ambient beds — fast and very affordable.

    Try it

Sound effects

Foley, ambience and sound design from a description.

3 models

  • Sound Effects v2

    ElevenLabs

    Top pick

    Any sound from a description — foley, ambience, UI sounds.

    Try it
  • Auto Soundtrack

    Kuaishou

    Adds matching sound effects and background music to a silent video.

    Try it
  • MMAudio (video → sound)

    Open source

    Best value

    Generates synchronized sound for a silent video clip.

    Try it

Avatars & lip-sync

Talking presenters and dubbing with natural lip movement.

5 models

  • OmniHuman 1.5

    ByteDance

    Top pick

    One photo + audio → a realistic talking, gesturing presenter.

    Try it
  • Kling Avatar 2.0 Pro

    Kuaishou

    Expressive avatars from a single image, with natural head and hand motion.

    Try it
  • HeyGen Avatar IV

    HeyGen

    Studio-quality talking presenter from a photo, stable or expressive style.

    Try it
  • Lipsync 3

    Sync Labs

    Top pick

    Re-syncs lips in any existing video to new audio — perfect for dubbing.

    Try it
  • Lipsync 2

    Sync Labs

    Best value

    Re-syncs lips in an existing video to new audio — perfect for dubbing.

    Try it

Enhance

Upscaling, cleanup and background removal.

5 models

  • Video Upscale 4K

    ByteDance

    4K

    Upscale any video to 1080p, 2K or 4K with sharper detail and less noise.

    Try it
  • Topaz Video Upscale

    Topaz Labs

    Pro-grade Topaz restoration and upscaling for footage and AI clips.

    Try it
  • Image Upscale

    Topaz Labs

    Upscale and enhance images with creative detail restoration.

    Try it
  • Remove Background

    Bria

    FastBest value

    Pixel-perfect background removal for any image.

    Try it
  • Video Background Removal

    Bria

    Remove or replace the background of any video — no green screen needed.

    Try it

Try every model with 100 free credits.

No credit card. No separate sign-ups. Just create.

100 free credits · No credit card