Promote Sign in Sign up

Catalogs

Models

193 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17
Weights and source · filters active
Open weights Closed On Hugging Face Clear filters
Most downloaded A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose models

Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.

Understand our sources and data limits

  1. Muranyi 2 Tesana Tesana is an AI game-generation platform using the Muranyi 2 game model to generate playable games,… Multimodal · Closed Closed weights
  2. Muse Voice Transcribe Meta Platforms Muse Voice Transcribe is a real time audio perception model that performs streaming speech recognit… Multimodal · Closed Closed weights
  3. Music v2 ElevenLabs Music v2 is ElevenLabs’ closed-source AI music model for generating, editing, remixing, and inpaint… Multimodal · Closed Closed weights
  4. Navigator n1.5 Yutori Navigator n1.5 is Yutori’s web computer-use model for autonomous browser tasks. It combines human-l… Multimodal · Closed Closed weights
  5. Odyssey 2 Max New Odyssey Odyssey 2 Max appears to be Odyssey’s newest high-end AI video model tier, positioned above earlier… Multimodal · Closed Closed weights
  6. OmniCraft Texture Generator Deemos Technologies Hyper3D OmniCraft Texture is a 3D asset texturing tool that generates photorealistic, seamless, til… Multimodal · Closed Closed weights
  7. Ontology 1 Onton Ontology 1 is a neurosymbolic search model that reasons over an explicit, self-expanding knowledge… Multimodal · Closed Closed weights
  8. OpenRouter Speech to Text OpenRouter OpenRouter STT is OpenRouter’s unified speech-to-text interface for accessing transcription models… Multimodal · Closed Closed weights
  9. Pan-4B Pantograph Pan-4B is a 4 billion parameter goal-conditioned agent from Pantograph that plays Minecraft. It is… Multimodal · Closed Closed weights
  10. Phoenix 3 Tavus Phoenix-3 is Tavus’ full-face real-time rendering model for hyper-realistic conversational avatars… Multimodal · Closed Closed weights
  11. Phoenix 4 Tavus Phoenix-4 is Tavus’ real-time human rendering model that generates continuous facial behavior with… Multimodal · Closed Closed weights
  12. Pi 0.7 Physical Intelligence π 0.7 is Physical Intelligence’s steerable general-purpose vision-language-action robot model. It i… Multimodal · Closed Closed weights
  13. PikaSteam 1 Mellis PikaStream 1.0 appears to be Pika’s real-time model for live video chat agents. Based on the post y… Multimodal · Closed Closed weights
  14. PixVerse C1 Pixverse PixVerse C1 appears to be PixVerse’s newer video generation model tier in its API lineup. The docs… Multimodal · Closed Closed weights
  15. PixVerse R1 Pixverse PixVerse R1 is a real-time world model that streams interactive 1080p video, generating infinite, p… Multimodal · Closed Closed weights
  16. PixVerse V6 Pixverse PixVerse V6 is PixVerse’s AI video generation model focused on longer, more production-ready clips.… Multimodal · Closed Closed weights
  17. PP OCRv6 Baidu PP-OCRv6 is PaddlePaddle/Baidu’s lightweight universal OCR system for multilingual text detection a… Multimodal · Closed Closed weights
  18. Qwen 3.7 Plus Alibaba Qwen3.7-Plus is Alibaba Qwen’s multimodal agent model that unifies vision and language for agentic… Multimodal · Closed Closed weights
  19. Raven 0 Tavus Raven-0 is Tavus’ real-time perception model that continuously interprets what it sees to add visua… Multimodal · Closed Closed weights
  20. Reve 2.0 Reve AI Reve 2.0 is Reve AI’s closed-source image generation and editing model for native 4K image creation… Multimodal · Closed Closed weights
  21. S1 Skild AI S1 is a robotic foundation model for manipulation that learns tasks in context from a single video… Multimodal · Closed Closed weights
  22. S1 Voice Superwhisper S1-Voice is Superwhisper’s cloud speech-recognition model for high-accuracy, low-latency transcript… Multimodal · Closed Closed weights
  23. SANA WM (Bidirectional) NVIDIA SANA-WM Bidirectional is Efficient-Large-Model’s open-source 2.6B image-to-video world model for 72… Multimodal · Closed image to video pipeline
  24. Seed 1.5 ByteDance Mixture-of-experts Seed1.5 (Doubao-1.5-pro) large language model that balances high performance wit… Multimodal · Closed Closed weights
  25. Seed 1.5 VL ByteDance Compact vision-language foundation model from ByteDance Seed, combining a 532M vision encoder with… Multimodal · Closed Closed weights
  26. Seed 1.8 ByteDance General-purpose agentic model that unifies LLM and VLM abilities with search, code execution and GU… Multimodal · Closed Closed weights
  27. Seed 2.0 ByteDance Seed 2.0 is described publicly only as a new ByteDance Seed language model for Doubao, but there is… Multimodal · Closed Closed weights
  28. Seed 2.0 Pro ByteDance Dola-Seed-2.0-Preview is ByteDance Seed’s general-purpose multimodal model released for public eval… Multimodal · Closed Closed weights
  29. Seedance 2.0 ByteDance Seedance 2.0 is ByteDance's multimodal AI video model that turns text plus image, video and audio r… Multimodal · Closed Closed weights
  30. SeedRealtime ByteDance SeedRealtime is a native audio-visual full-duplex LLM that jointly processes audio, video, and text… Multimodal · Closed Closed weights
  31. Silk 1 Rumik Silk 1 Beta is Rumik AI’s expressive text-to-speech model for AI companions, focused on emotional v… Multimodal · Closed Closed weights
  32. Sparrow 0 Tavus Sparrow-0 is Tavus’ conversational timing model that manages turn-taking so voice and video agents… Multimodal · Closed Closed weights
  33. Starchild 1 Odyssey Starchild-1 is Odyssey’s real-time multimodal world model that generates synchronized audio and vid… Multimodal · Closed Closed weights
  34. SWE 1.5 Cognition SWE-1.5 is Cognition’s fast software-engineering agent model designed for strong coding performance… Multimodal · Closed Closed weights
  35. Sync 3 sync. Sync-3 is Sync.’s advanced lipsync and visual dubbing model for video localization. It is built to… Multimodal · Closed Closed weights
  36. Synthesia Express-1 Synthesia Express-1 is Synthesia’s closed-source avatar video model for generating expressive AI avatar perfo… Multimodal · Closed Closed weights