Model Gallery
Browse all available AI models. Click any model to try it in the Playground.
AssemblyAI Universal 2
High-accuracy speech recognition with speaker diarization and real-time streaming.
AudioCraft Stereo
Meta's music and audio generation model with stereo output and style control.
Deepgram Nova 3
Ultra-fast speech-to-text with 99%+ accuracy and low latency streaming.
ElevenLabs Multilingual v3
Lifelike multilingual voice synthesis with emotion and accent control.
ElevenLabs Turbo v3
Low-latency TTS optimized for real-time conversational applications.
Kokoro TTS
Open-weight text-to-speech with natural prosody and multiple voice styles.
MusicGen Large
Generate high-quality music from text prompts with melody conditioning.
OpenAI TTS HD
Premium neural TTS with studio-quality output across six natural voices.
OpenAI TTS Standard
Fast and cost-effective text-to-speech for production workloads.
Suno v4.5
AI music generation with vocals, lyrics, and full song structure from text.
Udio v2
High-fidelity AI music creation with genre and instrument control.
Whisper Large v3 Turbo
OpenAI's fastest multilingual speech recognition model with 99 language support.
Aura Flow
Fast and expressive image generation with strong prompt adherence.
Aurora
Photorealistic image synthesis with advanced lighting and detail rendering.
Flux 2 Max
Highest-quality Flux generation with maximum resolution and detail.
Flux 2 Pro
Professional-grade image generation with superior composition and realism.
Flux Dev
Open-weight Flux model for development and research use cases.
Flux Dev LoRA
Flux Dev with LoRA fine-tuning support for custom styles and subjects.
Flux Pro
State-of-the-art image generation with exceptional prompt understanding.
Flux Pro LoRA
Flux Pro enhanced with LoRA adapters for personalized image generation.
Flux Pro Ultra
Ultra-high resolution Flux generation up to 4MP with raw photo mode.
Flux Schnell
Fastest Flux model — 4-step generation for rapid prototyping.
GPT-Image 1.5
OpenAI's latest image generation model with world-class instruction following.
Gemini 3 Pro Image
Google's multimodal image generation with deep reasoning and editing.
Ideogram v2
Best-in-class text rendering in images with accurate typography.
Ideogram v2 Turbo
Fast Ideogram generation with excellent text accuracy at lower cost.
Kolors
Kuaishou's text-to-image model with vibrant colors and Chinese aesthetic.
Playground v3
Creative image generation with strong artistic style and composition control.
Recraft v3
Professional design-focused image generation with vector and raster output.
SDXL
Stable Diffusion XL — high-resolution open-source image generation.
SDXL Lightning
Ultra-fast SDXL variant with 4-step distillation for instant results.
Seedream 4.5
ByteDance's latest image generation with rich detail and style diversity.
Stable Diffusion 3.5 Large
Stability AI's flagship model with improved composition and photorealism.
Stable Diffusion 3.5 Medium
Balanced SD3.5 variant offering quality and speed for production use.
Stable Diffusion 3.5 Turbo
Fastest SD3.5 model for rapid iteration and high-volume generation.
Background Removal
Precise AI-powered background removal with edge refinement for any subject.
Face Enhancement
Restore and enhance facial details, fix blur, and improve skin texture.
Image Colorization
Automatically colorize black-and-white photos with realistic colors.
Image Inpainting
Fill or replace selected regions using AI-guided content-aware synthesis.
Image Outpainting
Extend image boundaries beyond the original frame with coherent content.
Image Upscaler 4x
Upscale images up to 4× with AI super-resolution and detail enhancement.
Object Removal
Remove unwanted objects from photos with seamless background fill.
SeedVR2 Upscaler
Video-aware upscaling for consistent quality across frames and motion.
Style Transfer
Apply artistic styles to photos while preserving structure and content.
CogVideoX 5B
Open-source video generation with smooth motion and scene consistency.
Hunyuan Video
Tencent's high-quality video synthesis with cinematic motion and detail.
Kling Video v3 Pro
Professional video generation with advanced physics and camera control.
Kling Video v3 Standard
High-quality video generation with natural motion and scene transitions.
LTX Video
Real-time video generation optimized for low latency and interactivity.
Minimax Video 01
Cinematic AI video with expressive characters and dynamic storytelling.
Pika 2.2
Creative video generation with precise motion control and style transfer.
Seedance v1.5
ByteDance's video model with fluid motion and high temporal consistency.
Sora 2
OpenAI's world-model video generator with deep physical understanding.
Veo 3.1
Google DeepMind's flagship video model with photorealistic output and audio.
Veo 3.1 Fast
Faster Veo 3.1 variant for rapid video prototyping at reduced cost.
Wan 2.2
Alibaba's open-source video generation with strong motion quality.
All models are accessible via a single API key with pay-as-you-go pricing.