KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. It uses a two-stage pipeline combining a large language model and an efficient audio codec to achieve excellent speed and audio quality. This model supports Spanish, has 400 million parameters, and a sampling rate of 22kHz.

Audio ProcessingTransformersSpanish

KaniTTS is a high-speed, high-fidelity Arabic text-to-speech model optimized for real-time conversational artificial intelligence applications. It adopts a two-stage pipeline architecture, combining a large language model with an efficient audio codec to achieve excellent speed and audio quality, and can meet the speech synthesis needs of multiple fields such as conversational AI, accessibility assistance, and research.

Audio ProcessingTransformersArabic

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. Through a unique two-stage architecture that combines a large language model with an efficient audio codec, it achieves low-latency and high-quality speech synthesis, with a real-time factor as low as 0.2, which is 5 times faster than real-time speed.

Audio ProcessingTransformersEnglish

KaniTTS Pretrain v0.3 is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. It uses a two-stage pipeline architecture that combines a large language model and an efficient audio codec to achieve extremely low latency and high-quality speech synthesis.

Audio ProcessingTransformersMultiple Languages

xLSTM-7b-Instruct is an experimental fine-tuned version based on NX-AI/xLSTM-7b, specifically optimized for instruction-following tasks. This model adds support for chat templates and uses TRL for supervised fine-tuning training, aiming to provide a better conversational interaction experience.

Natural Language ProcessingTransformers

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. It adopts a two-stage pipeline architecture, combining a large language model and an efficient audio codec, achieving excellent speed and audio quality. It supports multiple languages and is suitable for edge/server deployment.

Audio ProcessingTransformersMultiple Languages

This is a conversational AI assistant focused on Finnish dental medicine. It is a large language model fine-tuned with LoRA and can generate structured clinical responses for dental consultation questions, divided into three parts: background, assessment, and suggestions.

Natural Language ProcessingTransformersOther

Nous-V1 8B is an 8-billion parameter language model developed by Apexion AI, built on the Qwen3-8B architecture. This model is designed for various natural language processing tasks and performs excellently in areas such as conversational AI, knowledge reasoning, code generation, and content creation. It strikes a good balance between model capabilities and actual deployment efficiency.

Natural Language ProcessingTransformersMultiple Languages

This is a conversational AI model fine-tuned based on LLaMA-3-8B, specifically designed to provide empathetic and unbiased support for mental health guidance. The model is fine-tuned using a carefully curated mental health dataset and can provide considerate and supportive responses, simulating therapeutic conversations.

Natural Language ProcessingTransformersEnglish

Poro 2 8B Instruct is an instruction - following chatbot model based on the Llama 3.1 8B architecture, designed for conversational AI applications in Finnish and English.

Natural Language ProcessingTransformersMultiple Languages

A dialogue model fine-tuned based on Gemma 27b, aiming to replicate the text quality of Claude 3, supporting ChatML format for conversational interactions.

Natural Language ProcessingGgufEnglish

This is a small language model trained from scratch on the TinyChat dataset, aiming to achieve natural conversational responses with minimal model size.

Natural Language ProcessingTransformers

ArrowPro-7B-KUJIRA is a Japanese-optimized model based on the Mistral series, specifically designed for AI virtual streamers and AI assistants, featuring outstanding conversational performance and prompt injection defense capabilities.

Natural Language ProcessingTransformers

EMO-2B is a 2.5-billion-parameter conversational AI model designed for emotionally resonant dialogues, capable of providing nuanced and context-appropriate emotional responses.

Natural Language ProcessingTransformers

Dolphin 2.9 is an uncensored AI assistant model based on Llama-3-70b, featuring multiple instructions, conversational skills, and programming capabilities, with preliminary support for agent functionality and function calling.

Natural Language ProcessingTransformersEnglish

ConvAI-9b is a conversational AI model with 9 billion parameters, built by merging Zephyr-7b-beta and Mistral-7B-v0.2, suitable for interactive scenarios such as chatbots and virtual assistants.

Natural Language ProcessingTransformersEnglish

Yuna AI is a conversational AI assistant designed for emotional companionship, featuring highly human-like interaction capabilities

Natural Language ProcessingGgufMultiple Languages

Dolphin 2.2 is an open-source AI assistant fine-tuned based on the Yi model, featuring a 200k context length and enhanced conversational empathy capabilities. While uncensored, it has undergone dataset filtering to improve quality.

Natural Language ProcessingTransformersEnglish

A conversational assistant model based on Mistral-v0.1, trained with a mix of AIRIC dataset and multiple public datasets, equipped with social dialogue capabilities.

Natural Language ProcessingTransformers

MommyGPT-3B is a conversational AI fine-tuned on the OpenLLaMa 3B V2 model, simulating a maternal figure to provide caring dialogue

Natural Language ProcessingTransformersEnglish