NextChat Releases

This release introduces group chat functionality, voice activity detection using Silero-VAD, and support for CosyVoice2 text-to-speech. It also adds a standalone frontend for ASR/TTS tools and simplifies the setup process with one-click CUDA support.

Feb 19, 2025

Feature-rich release adding DeepSeek provider integration, MCP (Model Context Protocol) support, and numerous new model additions including Gemini 2.0, OpenAI o3-mini, and SiliconFlow provider.

Feb 16, 2025

This release represents a complete rewrite of the backend and frontend, transforming the application into a VTuber platform with vision capabilities, desktop pet mode, and support for various LLMs including DeepSeek R1.

Feb 4, 2025

This is a bug fix patch that addresses Nvidia GPU compatibility issues by reverting the default ASR provider back to FunASR.

Dec 21, 2024

Release adding OpenAI Realtime API support for real-time voice interactions, along with Claude 3.5 Haiku support and various bug fixes.

Nov 11, 2024

Release adding ChatGLM model support and Claude 3.5 Sonnet/Opus latest versions, along with various improvements and bug fixes.

Nov 5, 2024

Minor release adding XAI (x.ai/Grok) provider support for using Grok models in the application.

Oct 24, 2024

This release adds Google Gemini function call support, allows sending images only without text, and increases the o1 series model timeout to 4 minutes. It also includes frontend controls for code folding and various UI improvements.

Oct 15, 2024

Minimal release notes: "- Add `--version` flag, and make sure `--verbose` also prints the current version"

Oct 12, 2024

This release improves Google API integration with proper header authentication and fixes multiple bugs related to model compression and streaming responses. It also introduces Tauri stream fetch API in the App.

Oct 9, 2024

Minimal release notes: "Text output should be much cleaner now - the usage of multiple separators is finally working - one can include special"

Sep 27, 2024

This major release introduces text-to-speech (TTS), built-in plugins, audio/video playback support, and comprehensive model selector improvements. It also adds summarize model customization and manual title regeneration.

Sep 25, 2024

Sep 22, 2024

Minimal release notes: "- fix issue where the HTML parser would create some extra empty arrays - remove issue that caused too many layers of ne"

Sep 21, 2024

Minimal release notes: "- fix issues when reading HTML tables - fix issues related to HTML nesting"

Sep 16, 2024

This release adds official support for OpenAI's o1 model and the chatgpt-4o-latest model. It also introduces keyboard shortcut functionality and various UI bug fixes.

Sep 13, 2024

This is a hotfix release that fixes Mermaid diagram rendering issues, adds crossOrigin attributes for the web manifest, and corrects default plugin configuration.

Sep 7, 2024

This release introduces plugin support for GPTs-like actions based on function calls, adds a dedicated page to search chat history, and implements IndexedDB for better data persistence.

Sep 6, 2024

Adds quality and style options for DALL-E 3, fixes logic regarding GPT-4 restrictions, improves accessibility, and introduces Baidu API support.

Aug 16, 2024

Supports the DALL-E 3 model, integrates Moonshot and Tencent APIs, and adds UI improvements like code folding and font-family configuration.

Aug 6, 2024