An agent framework that connects digital humans (2.5D, 3D, mobile, PC, web) and LLMs (OpenAI-compatible, DeepSeek) to business systems.
13.6K2.4KPythonGPL-3.0Updated 29 days ago
- Stars
- 5,668
- Forks
- 840
- Open issues
- 5
- Last commit
- 13 hours ago
What is it?
AIGCPanel is a desktop application for creating AI digital human videos and audio. It runs on Windows, macOS and Linux, and lets users combine a portrait or avatar video with text or an audio file, using open-source lip-sync models such as MuseTalk, LatentSync, Wav2Lip and Heygem to produce the result.
The app covers speech synthesis and voice cloning with models including CosyVoice, FishSpeech, IndexTTS and SparkTTS, plus speech recognition through FunASR with timestamped output and subtitle export. A toolbox of more than 25 audio and video utilities handles tasks such as subtitle generation, video compression, speed changes and text-to-image generation. Local models can be imported, started and stopped from a single interface, and remote API models can be connected as well.
A command-line tool named aigcpanel exposes the installed model services and built-in tools for scripting. Some features, including the visual workflow editor, live-stream interaction and cloud model services, are marked as VIP.
Key features
- 01Lip-sync video synthesis with MuseTalk, LatentSync, Wav2Lip and Heygem models
- 02Text-to-speech, voice cloning and speech recognition with timestamped subtitle export
- 03More than 25 audio and video processing tools in a built-in toolbox
- 04One-click import, start and stop of local AI models, with remote API model support
- 05Command-line interface for listing and calling model services from scripts
Use cases
- Producing short talking-head videos from a script and an avatar clip
- Cloning a voice from a reference recording for narration
- Generating subtitles for video content through speech recognition
- Running local open-source TTS and lip-sync models without writing code
Quick start
- 1
Download the installer for your platform from aigcpanel.com
- 2
Install on Windows by double-clicking the .exe package
- 3
Run the AppImage on Linux
chmod +x AIGCPanel.AppImage && ./AIGCPanel.AppImage - 4
Open the app, go to model management and download a one-click startup package for the model you need
Things to know
- Several models and the workflow and live-streaming features require a paid VIP tier.
- Some features depend on large local AI models, which need substantial disk space and typically a capable GPU.
- The README notes that the product must not be used for unlawful purposes and must comply with Chinese law.
Topics
FAQ
- What is aigcpanel?
- A desktop app for building AI digital humans, with lip-sync video synthesis, text-to-speech, voice cloning, and local AI model management. AIGCPanel is a desktop application for creating AI digital human videos and audio. It runs on Windows, macOS and Linux, and lets users combine a portrait or avatar video with text or an audio file, using open-source lip-sync models such as MuseTalk, LatentSync, Wav2Lip and Heygem to produce the result.
- Is aigcpanel free to use? What license does it have?
- aigcpanel is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is aigcpanel still maintained?
- Actively maintained. The last commit to aigcpanel was on Oct 20, 2026.
- What can I use aigcpanel for?
- Producing short talking-head videos from a script and an avatar clip Cloning a voice from a reference recording for narration Generating subtitles for video content through speech recognition Running local open-source TTS and lip-sync models without writing code
- How do I install aigcpanel?
- Download the installer for your platform from aigcpanel.com Install on Windows by double-clicking the .exe package Run the AppImage on Linux: chmod +x AIGCPanel.AppImage && ./AIGCPanel.AppImage Open the app, go to model management and download a one-click startup package for the model you need
- Where can I get aigcpanel?
- The source code and installation instructions are on GitHub: https://github.com/modstart-lib/aigcpanel
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Windows-focused Gradio web app bundling text-to-speech, voice cloning, Whisper transcription, YouTube download, vocal separation and translation for dubbing.
13.2K1.9KPythonGPL-3.0Updated 3 months ago
Local, offline desktop studio for macOS and Windows that turns text into speech, clones voices, and generates songs with lyrics and MIDI scores.
1.7K128TypeScriptApache-2.0Updated 2 days ago
Local-first tool that turns a recorded talking-head clip and a script into a vertical MP4 with AI voice-over and automatic lip-sync.
48070TypeScriptMITUpdated 2 months ago
Open-source voice AI family from Microsoft, with long-form speech recognition (ASR), multi-speaker text-to-speech (TTS), and real-time streaming TTS models.
54.9K6.2KPythonMITUpdated 13 days ago
NVIDIA's open-source toolkit for building, fine-tuning and deploying speech AI models, covering speech recognition (ASR), text-to-speech (TTS) and speech LLMs.
18.6K3.7KPythonApache-2.0Updated 15 hours ago