English
An upgraded TTS system featuring multilingual support, real-time style switching and efficient inference
a powerful node-based AI workflow platform that enables local image, video, voice, and music generation with highly flexible and customizable workflows
Automatically generates HD short videos with script, footage, voiceover, subtitles and music
Zero-shot TTS system by Bilibili featuring fast voice cloning, cross-lingual synthesis, precise emotion/speed control
Turn Text into Realistic Podcasts with Multi-Speaker, Multilingual & Emotional Speech
Zero-shot voice cloning and natural-language-driven voice design across multiple languages and dialects
Generate 1-minute videos quickly with only 6GB of low VRAM.
An ultra-fast, lightweight open-source music model, delivering commercial-grade audio on local hardware with less than 4GB VRAM
A web-based 3D tool built with Three.js and React that lets users manually arrange models, set character poses, and adjust camera angles for quick storyboarding
A fast multimodal audio generation model supporting text and video conditioning for audio/music synthesis
Zero-shot cloning and emotional control across 23 languages
Clone voice in 5 seconds — GPT-SoVITS enables multilingual AI speech.
Automatically handles video translation, subtitle generation and dubbing
Supporting 600+ languages, voice design, voice cloning, natural speech, and ultra-fast inference
Upgraded model architecture with greatly improved sound quality and song integrity, supports ultra-long duration and multilingual creation
An open-source LLM-DiT speech model by Xiaohongshu featuring zero-shot cloning for 24 languages and 21 dialects
Delivers single-pass transcription, speaker diarization, and timestamping for long audio across 50+ languages
An AI cover and music remixing model that supports reference audio, lyrics, MIDI, and controllable musical styles
Removing hard-coded subtitles from videos and text watermarks from images with lossless resolution
A speech synthesis system that generates multi-speaker conversations with voice cloning and multilingual support.
Supporting Mandarin, English and Cantonese, with natural speech synthesis and zero-shot voice cloning
Highly expressive, long-form, multi-speaker conversational audio generation
Generates lightweight interactive 3D Gaussian scenes compatible with mainstream 3D software from one single image rapidly
A fast local AI audio platform supporting dozens of AI models, enabling voice generation, recognition, conversion, and music creation through an easy-to-use Web interface
Zero-shot voice cloning, supports multiple languages, allows voice parameter control
A joint zero-shot SVS project supporting multilingual synthesis and dual-mode control
Animate Digital Humans' Lip Movements
Featuring ultra-realistic 48kHz zero-shot voice cloning with rich emotional and lifelike expressiveness
Turns a simple description into a high-fidelity sound effect up to 30 seconds long, perfect for video voiceovers and game asset creation.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
Turns static portraits into video/audio-driven 3D models in real time
Clones voices from short audio and generates natural speech.
multilingual, real-time/offline recognition, easy to use and efficient
Multilingual support for 52 languages/dialects and exceptional robustness in song and contextual transcription
An open-source fast-thinking multilingual translation model supporting 33 languages
Voice cloning with text-tag control over 11 emotions, 4 paralinguistic sounds (like laughter/breathing), and 14 Chinese dialects
Clones voice and emotion from a short sample for accent-free dubbing across 14 languages
Transforms simple text prompts into up to 6 minutes of studio-quality music and lifelike sound effects
An open-source translation model, 33 languages + 5 dialects, accurate & flexible
Multilingual speech recognition, emotion & audio event detection—efficient and accurate
Generation and understanding, featuring high-fidelity song synthesis and controllable structural creation
A bilingual (English/Chinese) text-to-speech model built for ultra-low-latency streaming that enables text-driven voice creation, voice cloning, and fine-grained emotional control
a low-latency, real-time speech recognition model, featuring multilingual recognition and stable, continuous text output
Multi-language emotional expression, and real-time streaming generation to enable human-like natural speech with low-resource cross-scenario deployment.
A security-first workflow automation tool with enhanced reliability and efficiency, supporting visual drag-and-drop operation
Zero-shot voice cloning, emotion expression and streaming inference
Supporting 17 languages, with accurate dialect and low-volume recognition
An easy-to-deploy, extensible open-source AI chatbot
An expressive open-source text-to-speech model supporting 31 languages, featuring stable zero-shot voice cloning and precise inline pause control
A professional open-source image editor — layers, masks and type, reads/writes layered PSD files, fast even on big images.
Generate high-quality classical music, supports generation by period, composer and instrumentation
A self-hosted machine translation tool supporting multi-language translation, usable offline with controllable data privacy
Uses natural-language instructions to unify speech generation, editing, enhancement, and source separation
A workflow automation platform supporting no-code/code dual-mode building
Real-time talking-head framework, high-fidelity, long-duration stable audio-visual synchronization
A desktop graphical tool developed by ValueCell-ai based on OpenClaw, featuring one-click installation
A lightweight, efficient open-source document parser that accurately converts PDFs, images, and e-books into Markdown/JSON
An open-source vector-design app — pen and Bézier precision, resolution-free illustration that stays sharp at any zoom.
Supporting high-quality TTS and zero-shot voice cloning with extremely high timbre similarity
Seamless integration with chat apps like WeChat, DingTalk, and Feishu for multi-agent collaborative workflows
An open-source page-layout app — its own paragraph composer for magazines and books.
Turns lyrics into songs in seconds, generates music by style keywords.
Zero-shot voice cloning and expressive editing of emotion, style, and paralinguistic cues
An ultra-lightweight TTS tool, supporting multilingual speech synthesis and zero-shot voice cloning on ordinary CPU
Zero-shot voice cloning, emotion expression capabilities
Making local speech-to-text and translation easy.
Creates high-quality realistic sound effects from text or video with only English prompts supported
A vision-only, single-step generative image super-resolution model, featuring ultra-fast inference and superior restoration of fine text and structural details
Add perfectly fitting foley sounds to silent videos.
Taming Bad Noise for Effective Video Object Removal
PartPacker enables part-level 3D object generation from single-view images
An all-in-one local AI assistant supporting cross-platform operation and mobile remote control
Generates pixel-aligned high-fidelity 3D models with PBR textures from a single image
An open-source motion-graphics and compositing tool — ~306 built-in effects, no FFmpeg, fully AI-agent-drivable.
Get up and running with large language models
Easily displays technical and metadata information of audio and video files
Generates depth-aware 3D panoramas and scene models from single images
A cross-platform video editor offering broad format support, powerful filters, and easy timeline editing
An open-source video editor with its own codecs (no FFmpeg) — editing, color and sound in one app.
A desktop client for ChatGPT, Claude and other LLMs
A large model runner with a visual interface.
A smart-searchable library of 2000+ ready-to-use n8n automation workflows
A cross-platform software for high-performance live streaming and screen recording
An open-source word processor — reads/writes .docx with track changes, styles and scholarly references.
A lightweight and easy-to-use multi-terminal personal AI assistant, supporting multi-channel connection and custom skills
An open-source photo library and color-grading app — local storage, powerful grading, and fully AI-agent-drivable.
An open-source PDF workbench — read, organize, split and protect PDFs, with no account and no telemetry.
A free video editor featuring drag-and-drop simplicity, rich effects, and 4K video export
An open-source CAD drafting app — reads/writes DXF with a command line, object snaps, dimensions and plotting.
An open-source presentation app — reads/writes .pptx with transitions and animations, presents full screen in one click.
An open-source digital audio workstation — multitrack recording, a full mixer, MIDI and automation, scriptable by AI agents.
An open-source enterprise AI assistant integrating RAG pipelines, multi-modal interaction, and workflow orchestration.
An open-source spreadsheet — reads/writes .xlsx with formulas, PivotTables, charts and conditional formatting.
An open-source interface design app — auto layout, components with variants, design variables, prototyping and developer handoff
