Trending Repos

Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.

☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.

FL Studio v25.1.6.4997 — The best music production software. Info page and download link. Third-party software; all rights belong to the original authors.

Fast, concurrent inference for YuE2. Same model and recipe: 1.68× faster per song, 3.31× more songs per GPU.

FL Studio 2026 Producer Edition Premium Tools: release downloads, documentation, installation notes, and project updates.

🎙️ Real-Time Multi-Modal Speech Telemetry & Acoustic DSP Engine (FastAPI, Python 3.11, Autocorrelation Pitch, FFT Spectral Energy & Lexical Pacing Analytics).

Free, open-source Python CLI converting Serum 1/2 presets to Vital, with per-preset reports of approximations and unsupported features.

Word and phoneme level speech timing for spontanoues speech. Fast, accurate and robust.

End-to-end speech model research: waveform encoding, causal decoding, codec tokens, joint losses and streaming.

语音大模型研究工具包：音频指令数据、声学适配器、CPU 微型训练与推理、流式事件和评测。

Generate songs from a musical style and lyrics in ComfyUI using YuE2. Optional score viewing and editing, separate generation stages, and stereo 48 kHz audio output. Experimental.

tsov (the shape of voice) — hum it, get a song you can keep editing. A local-first, AI-native music workspace: humming → transcription → arrangement → mixing → export, with humans and agents sharing one command layer.

On-device audio transcription toolkit - trim, tag, transcribe and export recordings locally, with a Python engine and an Android demo app.

a music player that is integrated with soulseek for your downloaded music, auto lyrics that are synced and much more!

OpenSuno-YuE2: local music generation studio for the YuE2 model on Apple Silicon and Windows/NVIDIA, with automatic model downloads.

把一首歌的录音一键扒成 Synthesizer V 工程（SVP 153）/ MIDI / ABC 乐谱。全本地离线运行，带 Web UI，基于 M-A-P 的 SheetSage2 模型。

Find music and request it from Lidarr or nexcrate. Self-hosted, with accounts, quotas and recommendations.

Open-source music tools for AI agents. Compose in Python, synthesize instruments from code, and export WAV and MIDI.

A video harness work platform for Agents such as Claude or Codex: the agent writes the code that renders the film, checks its own frames, storyboard and cut. 给 Claude Code 和 Codex 用的视频Harness工作台：agent 写代码渲染成片、自己检查分镜，立意、成片由你拍板；众多风格预设、引擎丰富，配音配乐也用代码做。

Free, open-source real-time AI noise cancellation for Windows. A lightweight Krisp, NVIDIA Broadcast, & RTX Voice alternative for Steam, Discord, OBS, Teams, and Zoom. 100% offline, CPU-only, zero telemetry.

A DAW for AI agents: write music as text, read the audio back as text. MCP server, CLI and an agent skill.

Local, identity-aware speech transcription and diarization engine — turns multi-speaker audio into structured, named intelligence, 100% offline.

fnOS 飞牛音乐在线曲库扩展（fnmusic-ext）：无侵入接管官方音乐应用，接入网易云/酷我/咪咕/洛雪/喜马拉雅多音源在线搜播、每日推荐、多用户在线收藏、在线歌单增删、收藏与播放自动落盘。仅用 docker compose 部署，5 个容器一键拉起。

DAW Sync makes it easy for composers to collaborate across different OSs and DAWs.

Experimental FL Studio agent runtime: structured music plans, evidence-aware FAST workflows and a user-owned learning framework.

飞牛 fnOS 音乐扩展 fnmusic-ext：零侵入接管官方飞牛音乐，聚合网易云音乐 / 洛雪音乐 / 音乐DL 三音源，自带管理 WebUI，Docker 自托管，让飞牛音乐直接在线搜播并补全歌词与高清封面。

Unofficial fan tool: add your own songs to the EA Trax soundtrack of Burnout Revenge (PS2, PAL/USA) - with title, artist and album - keeping PCSX2 patches working.

Dubby 🎙️ — End-to-end YouTube video dubbing pipeline with language detection, ASR, word alignment, translation, voice cloning, and synchronized captions.

HardSID 4U over libusb on macOS and Linux — reverse-engineered USB protocol and a working Python driver

Local AI studio for images, edits, video, voice, music and sound effects on your own GPU. Use it at your desk, from your phone, or give it to your coding agents.

Joint Embeddings of DSP Effects Code and Audio

Talk to your Roland TR-8S and get a track back: a live studio, reverse-engineered SysEx, and an AI assistant on your own Claude subscription

The largest and most comprehensive MIDI dataset in the known galaxy

ADSR envelope state machine and band-limited wavetable synthesizer for tone and waveform synthesis.

ADSR envelope state machine and band-limited wavetable synthesizer for tone and waveform synthesis.

网易云/QQ/酷狗/Apple Music 榜单与歌单监控，自动择优下载指定音质 | go-music-dl orchestration layer

Movies, shows and music in one self-hosted app, with several versions per title and a page to discover what you are missing. One app instead of Radarr, Sonarr and Lidarr, and Bazarr still finds the subtitles.

三角洲行动自动钓鱼：三层判据（声音识别 + 电平区间 + 声像差方位）精确区分自己的鱼。纯系统音频检测，不注入进程、不读内存。

三角洲行动 口琴自动演奏工具 / 自动口琴脚本（Delta Force Harmonica Auto Player）。纯 Python 标准库零依赖，内置 8 首曲库、键位自定义、MIDI 解析与音频合成，含可交互网页演示。Delta Force harmonica auto-player written in pure Python stdlib.