Step 1
Choose a mode
Video, Image, Audio, or Transcription — all in one studio.
AI-powered multimodal studio
From nothing, everything.
Generate videos, images, audio, and transcriptions with AI in one studio.
Multi-model AI creative studio
Creators, studios & teams
Video, image, audio & transcription
How It Works
Step 2
Describe or upload
Use text prompts or upload reference material to guide the AI.
Step 3
Generate, refine & export
Iterate quickly, version your work, and export in high quality.
50+ AI models from 13 providers
All the best AI models,
one studio.
From Google Veo and OpenAI Sora to Midjourney and ElevenLabs — access every frontier model without switching apps.
🎬
Video
Generate cinematic videos from text prompts, reference images, or existing clips.
Google Veo 3.1
Text-to-VideoImage-to-VideoVideo Extend4K Upscale
Google Veo 3.1 Fast
Text-to-VideoImage-to-VideoVideo Extend
OpenAI
Sora 2
Text-to-VideoImage-to-Video
OpenAI
Sora 2 Pro
Text-to-VideoImage-to-Video
Kuaishou
Kling 3.0
Text-to-VideoImage-to-Video
Kuaishou
Kling 2.6
Text-to-VideoImage-to-VideoMotion Control
MiniMax
Hailuo 02 Standard
Text-to-Video
MiniMax
Hailuo 02 Pro
Text-to-VideoImage-to-Video
MiniMax
Hailuo 2.3 I2V
Image-to-Video
Alibaba
Wan 2.6
Text-to-VideoImage-to-VideoVideo-to-Video
Alibaba
Wan Speech-to-Video
Speech-to-Video
xAI
Grok Imagine Video
Text-to-VideoImage-to-Video
Kuaishou
Kling AI Avatar
Avatar Generation
InfiniTalk
InfiniTalk Lip Sync
Lip Sync
🎨
Image
Create and edit stunning images with the latest text-to-image and image-to-image models.
Imagen 4 Ultra
Text-to-Image2K Resolution
Imagen 4
Text-to-Image
Imagen 4 Fast
Text-to-Image
OpenAI
GPT Image 1.5
Text-to-ImageImage-to-Image
OpenAI
GPT Image 1 (4o)
Text-to-Image
Midjourney
Midjourney
Text-to-Image
xAI
Grok Imagine
Text-to-ImageImage-to-Image
ByteDance
Seedream 4.5
Text-to-ImageImage EditUp to 4K
ByteDance
Seedream 4.0
Text-to-ImageImage Edit
ByteDance
Seedream 3.0
Text-to-Image
Nano Banana Pro
Text-to-Image
Nano Banana Edit
Image Edit
Alibaba
Qwen Image
Text-to-ImageImage-to-Image
Z-Image
Z-Image Turbo
Text-to-Image
🎵
Audio & Music
Professional voice synthesis, sound effects, music generation, and audio processing.
ElevenLabs
TTS Turbo 2.5
Text-to-Speech21+ Voices
ElevenLabs
Multilingual V2
Text-to-SpeechMulti-language
ElevenLabs
Dialogue V3
Text-to-Dialogue
ElevenLabs
Sound Effect V2
Sound Effects
ElevenLabs
Audio Isolation
Voice Isolation
Suno
Suno Music
Music GenerationExtendAdd VocalsSeparate Vocals
📝
Transcription
Convert audio and video to text with high-accuracy speech recognition.
ElevenLabs
Scribe V1
Speech-to-TextTimestamps
New models are added regularly. More coming soon.
Quality & Safety
- Automated content filtering
- Report & block system
- Dedicated support contact
Integrations
- Multi-model generation via Kie.ai
- Voice synthesis via ElevenLabs
- Music generation via Suno
See NUL in Action
Demo video showcasing the multimodal creation workflow.
Pricing
Plans to try, create, and scale.
Pay As You Go
Try the studio
Free to start
- Purchase credit packs as needed
- Standard export quality
- Access to all modes and models
Pro Monthly
For creators
$9.99/mo
- 200 credits per month
- +10% bonus on credit pack purchases
- Priority processing
Pro Annual
Best value
$79.99/yr
- 300 credits per month
- +20% bonus on credit pack purchases
- Priority processing
- Save over 30%
| Feature | Pay As You Go | Pro Monthly | Pro Annual |
|---|---|---|---|
| Modes (video, image, audio, transcription) | All | All | All |
| Monthly credits included | None | 200 | 300 |
| Credit pack bonus | None | +10% | +20% |
| Export quality | Standard | High | High |
| Support | Priority | Priority |
FAQ
View allNUL is an AI-powered multimodal creative studio for generating and editing video, images, audio, and transcriptions — all in one app.
7 common questions to get you started.
Ready to create with NUL?
Available on iPhone, iPad, and Mac.