# Kedreamix/Linly-Talker

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬

Repository: https://github.com/Kedreamix/Linly-Talker
Canonical: https://ross.abutalabs.com/products/linly-talker
Homepage: https://kedreamix.github.io/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-02-10T05:17:05+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 8, longevity 75
- inputs: {"age_days": 1051, "days_push": 204, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3436, forks 533 (observed 2026-08-28T04:08:04.954049+00:00)

## What it is
Linly-Talker is a Python-based digital avatar conversational system that combines LLMs (Linly, Qwen, Gemini), speech recognition (Whisper, FunASR), TTS/voice cloning (Edge TTS, GPT-SoVITS), and talking head generation (SadTalker, Wav2Lip, ER-NeRF) into an interactive AI persona. It ships with a Gradio WebUI and FastAPI deployment for real-time dialogue with a virtual avatar driven from a single image or video.

## Use cases
- create a talking avatar from a photo
- build a digital human chatbot
- clone a voice from a short audio sample
- generate lip-synced talking head videos from text
- run an interactive AI assistant with a face
- experiment with talking head generation models

## When to choose
- you want an all-in-one digital avatar pipeline with LLM, ASR, TTS, and talking head generation
- you need a WebUI to quickly demo conversational avatars
- you want to swap between multiple THG models like SadTalker, Wav2Lip, and ER-NeRF

## When to avoid
- you need a production-grade, low-latency real-time avatar service
- you only need a single component like TTS or ASR
- you lack a GPU or cannot tolerate heavy model dependencies

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, llm-inference, chatbot, computer-vision, video-processing, web-framework
- domain: artificial-intelligence, large-language-models, speech-processing, computer-vision, chatbots, deep-learning
- platform: python, cross-platform
- tags: talking-head, digital-avatar, digital-human, voice-cloning, gradio-webui, lip-sync, asr, tts, sadtalker, wav2lip, er-nerf, gpt-sovits, whisper, gpu, docker, web-server

## Member repositories
- Kedreamix/Linly-Talker (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:04.954049+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:37:41.565071+00:00, confidence not recorded.
  - readme: https://github.com/Kedreamix/Linly-Talker (fetched 2026-08-28T04:08:04.954049+00:00, sha 4c1c92f9a155)
  - homepage: https://kedreamix.github.io/ (fetched 2026-08-29T09:31:47.678812+00:00, sha 9cdcacfcd0d0)
- Data as of 2026-08-30T08:39:29.467469+00:00.