Top AI Repos โ open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Digital Avatar Conversational System - Linly-Talker. ๐โจ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. ๐ค๐ค It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. ๐๐ฌ
| Date | Stars |
|---|---|
| 2026-07-31 | 3411 |
| 2026-08-02 | 3414 |
| 2026-08-03 | 3414 |
| 2026-08-06 | 3414 |
Today
โ stars today
This week
โ stars this week
This month
โ stars this month
Momentum
0.0
growth rate 0.00%/day
# Digital Human Intelligent Dialogue System - Linly-Talker โ 'Interactive Dialogue with Your Virtual Self' <div align="center"> <h1>Linly-Talker WebUI</h1> [](https://github.com/Kedreamix/Linly-Talker) <img src="docs/linly_logo.png" /><br> [](https://colab.research.google.com/github/Kedreamix/Linly-Talker/blob/main/colab_webui.ipynb) [](https://github.com/Kedreamix/Linly-Talker/blob/main/LICENSE) [](https://huggingface.co/Kedreamix/Linly-Talker) [**English**](./README.md) | [**ไธญๆ็ฎไฝ**](./README_zh.md) </div> **2023.12 Update** ๐ **Users can upload any images for the conversation** **2024.01 Update** ๐๐ - **Exciting news! I've now incorporated both the powerful GeminiPro and Qwen large models into our conversational scene. Users can now upload images during the conversation, adding a whole new dimension to the interactions.** - **The deployment invocation method for FastAPI has been updated.** - **The advanced settings options for Microsoft TTS have been updated, increasing the variety of voice types. Additionally, video subtitles have been introduced to enhance visualization.** - **Updated the GPT multi-turn conversation system to establish contextual connections in dialogue, enhancing the interactivity and realism of the digital persona.** **2024.02 Update** ๐ - **Updated Gradio to the latest version 4.16.0, providing the interface with additional functionalities such as capturing images from the camera to create digital personas, among others.** - **ASR and THG have been updated. FunASR from Alibaba has been integrated into ASR, enhancing its speed significantly. Additionally, the THG section now incorporates the Wav2Lip model, while ER-NeRF is currently in preparation (Coming Soon).** - **I have incorporated the GPT-SoVITS model, which is a voice cloning method. By fine-tuning it with just one minute of a person's speech data, it can effectively clone their voice. The results are quite impressive and worth recommending.** - **I have integrated a web user interface (WebUI) that allows for better execution of Linly-Talker.** **2024.04 Update** ๐ - **Updated the offline mode for Paddle TTS, excluding Edge TTS.** - **Updated ER-NeRF as one of the choices for Avatar generation.** - **Updated app_talk.py to allow for the free upload of voice and images/videos for generation without being based on a dialogue scenario.** **2024.05 Update** ๐ - **Updated the beginner-friendly AutoDL deployment tutorial, and also updated the codewithgpu image, allowing for one-click experience and learning.** - **Updated WebUI.py: Linly-Talker WebUI now supports multiple modules, multiple models, and multiple options** **2024.06 Update** ๐ - **Integrated MuseTalk into Linly-Talker and updated the WebUI, enabling basic real-time conversation capabilities.** - **The refined WebUI defaults to not loading the LLM model to reduce GPU memory usage. It directly responds with text to complete voiceovers. The enhanced WebUI features three main functions: personalized character generation, multi-turn intelligent dialogue with digital humans, and real-time MuseTalk conversations. These improvements reduce previous GPU memory redundancies and add more prompts to assist users effectively.** **2024.08 Update** ๐ - **Updated CosyVoice to offer high-quality text-to-speech (TTS) functionality and voice cloning capabilities; also upgraded to Wav2Lipv2 to enhance overall performance.** **2024.09 Update** ๐ - **Added Linly-Talker API documentation, providing detailed interface descriptions to help users access Linly-Talkerโs features via the API.** **20
Excerpt of 53,545 characters
Read on GitHub
Kedreamix
270
Kevin Ye ยท OpenAI Inc ยท China
11
2
2
StarRing
2
1
1
Would you bet a product on this? Bounded 0โ100 and slow moving.
matched fp:884a3fbb31439919, desc:talking head