Naver

Kanana-1.5-v-3B is a 3B-parameter vision–language model in Kakao’s Kanana line. It can process both images and text prompts, outputting grounded answers in natural language or structured JSON. It’s optimized for lightwe…

• 📜 OCR
• 🔍 Image recognition

CLOVA HyperCLOVA X THINK is Naver’s reasoning-focused LLM for Korean and English. Trained on ~6T tokens, it uses a Peri-LN Transformer with a three-stage pretrain (to 128K context) and post-training via SFT plus RL from…

• 🎵 Music recommendations
• 🔊 Text to speech
• 📈 Image gradients
• 📝 Note summaries

Kakao’s unified multimodal large model, capable of handling text, images, audio, and video in a single framework. It’s designed for fluid cross-modal reasoning, enterprise copilots, and creative generation, with strong…

• 📷 Images
• 💻 Coding
• 🎥 Videos
• 📚 Stories

CLOVA HyperCLOVA X SEED is NAVER’s lightweight, open-source line of models (0.5B, 1.5B, 3B parameters) aimed at commercial use. The “SEED Think 14B” version adds deeper reasoning, pruning/distillation, and advanced trai…

• 💬 Chatting
• 💻 Coding
• 📝 Writing
• 🖋️ Tattoos

CLOVA HyperCLOVA X SEED Vision (3B) is NAVER’s lightweight multimodal model capable of understanding images and text (plus video frames) and answering in text. It supports visual question answering, chart/diagram interp…

• 📷 Images
• 📝 Writing
• 📄 Resumes
• 🖼️ Logos

2.1B is the smallest model in Kakao’s Kanana family—built on 2.1 billion parameters. It’s designed for lightweight assistants, chatbots, and mobile/edge use cases where speed, cost, and efficiency matter most.

• 🤖 Chatbots
• 📞 Customer support
• 💬 Chatting
• 💼 Personal assistant

Kanana Kinema by Kanana is Kakao’s generative video model. It turns text prompts, images, or reference clips into high-quality, temporally stable video with controllable style, motion, and pacing—built for creative prod…

• 🎥 Videos
• 🎬 Video editing
• 📝 Content

Kanana Kollage by Kanana is Kakao’s multimodal creative model, designed for generating and combining diverse media—text, images, layouts, and styles—into coherent outputs. It’s aimed at enterprise and creator workflows…

• 🖼️ Image generation
• 🖌️ Image editing
• 📝 Writing
• 📷 Images

NAVER’s neural text-to-speech service for lifelike, multilingual voices. It offers natural prosody, style controls, SSML, real-time streaming, and brand-safe custom voice options—ready for apps, call centers, e-learning…

• 🔊 Text to speech

NAVER’s clinical speech solution for hospitals and clinics. It transcribes doctor–patient conversations and dictations in real time, inserts medical terminology correctly, and formats notes for EMR systems—reducing afte…

• 🗒 Transcription

CLOVA Korean language model with 82B parameters.