WeVisOne-VL
WeChat Vision's unified perception model — detection, OCR, segmentation, matting…
Tencent WeChat Vision's open VLM unifies detection, OCR, counting, segmentation and alpha matting in one model. 2B/4B sizes, NOASSERTION license, 1k stars.
Published entries filed under “Audio” in GitHub, newest first by publication date on this site.
39 entries
WeChat Vision's unified perception model — detection, OCR, segmentation, matting…
Tencent WeChat Vision's open VLM unifies detection, OCR, counting, segmentation and alpha matting in one model. 2B/4B sizes, NOASSERTION license, 1k stars.
Tsinghua's 2B open TTS with 30-language cloning at 48kHz studio quality
Tsinghua NLP lab's open TTS: 2B params, 30 languages, voice design, controllable cloning, 48kHz output, RTF as low as 0.3. Apache-2.0.
one authorized portrait and a script in, a QA-passed presenter video out
Lanshu's agent skill runs the full presenter-video line — script, voice, digital human, lip-sync, render, QA — plus a 12-style route. MIT, 2,924 stars.
turn a Chinese story into a hand-drawn page-flip animation
An open-source agent skill turning Chinese stories into 3:4 hand-drawn flipbook MP4s — 327 style assets, hand-written text in the art, Remotion rendering, MIT.
Free Cross-Platform Streaming, No Login or Ads
Open-source music app streaming and downloading on Android, iOS, macOS, Windows and Linux; imports Spotify playlists, trends in 75+ countries, no account, MIT.
A self-hosted film catalog with DHT search
mediasite combines TMDB charts, ratings, and magnet search through a self-hosted bitmagnet stack; setup requires Docker and a TMDB key.
the open-source Mac singing trainer that shows exactly where you go off-key
A free, open-source Mac singing trainer: play a song in Spotify, sing along, and it learns the melody on-device and scores every line you sing. MIT.
live bilingual subtitles from system audio, fully offline
AudioScript listens to system audio or your mic, transcribes and translates locally with sherpa-onnx and opus-mt, and overlays English-Chinese subtitles.
real-time face swap from one photo, and its limits
Deep-Live-Cam is an AGPL-3.0 real-time face swap tool driven by a single photo, with an ethics statement and content checks in the README. Consent required.
give your coding agent ears
earshot is an open-source Python toolkit that lets AI agents hear: describe sounds, score fit, find best moments, spot synthetics, make sound in code.
on-device simultaneous interpretation on Apple Silicon
VoxWeft ports VoxCPM2 to MLX for on-device interpretation: first audio in about 170 ms, 30 languages, 5-second voice cloning, nothing leaves the machine.
real-time rendering of gray-box video into detailed frames
EdenLive, from VAST, renders gray-box video into detailed frames in real time for game prototypes. Code is Apache-2.0; weight licenses vary.
open speech and audio models
Ming 3.0 TTS, ASR and audio understanding: 0.5B and 7.9B TTS variants, context-aware transcription, and a 126B audio model with demanding GPU needs.
AI erases hardcoded subtitles and paints the background back in
VSR finds hardcoded subtitles with PaddleOCR, then inpaints the background with LAMA, STTN or ProPainter. Local and lossless, Apache-2.0.
open-source music generation that writes an editable score first
YuE2 is an open-source music generation model for creators who edit melodies before rendering vocals. Code is Apache-2.0; weights are CC BY-NC 4.0.
a native Rust Spotify desktop client without a browser engine
Spotifast is a cross-platform Rust Spotify client with no browser engine, typically 100–250 MB of RAM, plus Connect and a Winamp mini player. Premium required.
streaming video understanding model
Streaming video-understanding model: it processes video in chunks and answers from updated memory. The repo has docs only; weights are not released.
trim video in seconds without re-encoding
LosslessCut wraps FFmpeg stream copy in a cross-platform GUI: trim camera, drone or lecture footage in seconds with no re-encode and no quality loss.
a topic in, a finished short video out
MoneyPrinterTurbo is an open-source AI video generator: give it a topic and it writes the script, matches footage, adds voiceover and renders a 1080p cut. MIT.
record demo videos that look edited, for free
Recordly is an open-source Screen Studio alternative: auto-zooms, cursor polish and styled frames, exporting MP4 or GIF on macOS, Windows and Linux.
record your screen, edit frame by frame, save a GIF
ScreenToGif is the veteran open-source Windows recorder for GIFs: capture an area, edit frame by frame, export GIF, APNG, video or PSD. Portable, no install.
edit videos with Claude Code
video-use from browser-use hands video editing to a coding agent: drop footage in a folder, chat your edits, get final.mp4 with filler cut and subtitles.
one-click subtitle translation and dubbing
VideoLingo turns video translation into a one-click pipeline: word-level alignment, AI segmentation, glossary translation and dubbing with voice cloning.
an ElevenLabs-style voice studio, local and open source
VoiceStudio is an open-source ElevenLabs alternative: cloning, dubbing and transcription run locally across 17 TTS and 9 ASR engines, plus MCP for agents.
turn editing plans into editable JianYing drafts
Turns editing plans into editable JianYing multi-track drafts on a Mac, then exports MP4 via the native engine. Multi-track, PIP, subtitles, keyframes.
download video from anywhere, right in your terminal
A yt-dlp-powered terminal downloader for YouTube, X, TikTok and 1,800+ sites — paste a link, pick a resolution. Audio to MP3, MIT, no Python.
type a topic, get a finished short video
Pixelle-Video is Alibaba's open-source AI engine that turns a topic into a finished short video: script, visuals, voiceover and music in one run. Apache-2.0.
a streaming digital human that talks back live
LiveTalking by lipku is a real-time streaming digital human: synced audio-video, interruptible speech, multi-session, low-latency WebRTC, Apache-2.0.
talking-head video from one photo
Meituan's LongCat team open-sourced a model that turns one photo and one audio track into a talking video — Whisper lip sync, 8-step distillation, MIT.
open-source voice cloning from a short sample
VoxCPM2 by OpenBMB is a 2B-parameter open TTS: 30 languages, 48kHz output, Apache-2.0 licensed, so voiceovers and podcasts can run on your own machine.
turn your AI coding assistant into a video studio
OpenMontage turns your AI coding assistant into a video studio: 12 pipelines, a storyboard approval gate with per-asset cost, free without any API key.
turn long videos into post-ready clips, locally
AutoClip is an open-source video clipper for long-form material: feed it an interview, podcast, lecture or gaming VOD and it mines the subtitles for an outline, scores segments for highlight-worthiness and cuts clips you approve before anything renders. Unlike cloud clipping services, cutting and rendering stay on your machine with your own model keys — fully offline via Ollama. It ships as a desktop app, a Docker stack and a CLI/MCP pipeline, with export presets for Douyin, Shorts and Bilibili.
turn any topic into a narrated explainer video
html-explainer is an open-source Agent Skill for Claude Code, Codex and other coding agents: give it a topic and it runs research, narration, voiceover, subtitles, frame-by-frame rendering and covers end to end, producing a hard-subtitled MP4. Scenes are written in HTML/CSS/GSAP and rendered with a deterministic seek renderer, so audio and animation stay locked in sync. The default edge-tts voiceover is free and everything runs locally.
an open-source voice studio that never leaves your machine
The usual way to narrate a video is pasting a script into a cloud TTS: per-character pricing, generic voices, and your unpublished text on someone else's server. yovoice runs 7 local TTS models through audio.cpp on your own hardware, clones a voice from a 1-60 second clip, and ships a full record-trim-export workflow plus a CLI and an Agent Skill. Apache-2.0, for macOS and Windows.
one-click AI-generated story videos
The open-source tool Story-Flicks takes nothing but a story theme and automatically produces a complete short video with AI illustrations, narration, and subtitles; the text model can connect to DeepSeek, Alibaba Cloud, OpenAI, and other providers, with one-command Docker deployment and multi-language output.
Turn Audio and Video into Structured Notes, Locally
AudioNotes runs speech recognition locally with FunASR, turning transcripts into Markdown via a local Ollama model, keeping data on-device for meetings.
an open-source cross-platform player with pluggable sources
An open-source music client built with Flutter that covers desktop and mobile; music sources, playlists, and metadata are all plugged in, playback runs locally with no telemetry, and tracks can be downloaded with tags for offline listening.
A Go-based Cross-platform Command-line Video Downloader
Lux is a command-line video downloader written in Go that resolves real stream URLs across 45 sites including Bilibili, Douyin, and YouTube, with quality selection, subtitle downloads, batch playlist fetching, and resumable downloads.
A Local Ebook-to-Audiobook Converter
An open-source tool that converts ebooks into audiobooks entirely on your own machine, with multiple built-in TTS engines, voice cloning, and support for 1,158 languages, producing an m4b with chapters and metadata — no cloud service needed, and it runs on as little as 2GB of RAM.