[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
-
Updated
Feb 5, 2025 - Python
[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
可控 Foley / 环境声生成框架:文本与时序条件驱动,扩散与流匹配声学模型,Griffin-Lim 声码器,纯 numpy/scipy、离线优先
Codex skill for Doubao Seed Audio: voiceover, dialogue, ambience, Foley, subtitles, and Seedance audio post-production.
Sonic Blueprint Engine — AI Foley artist and soundscape blueprint generator. Turn images and audio into layered sound design and Suno-ready prompts.
Mirelo SFX Kiro Power — generate and edit sound effects, Foley and ambience for video from the Kiro agent, via the hosted Mirelo MCP server.
Unified facade for sourcing, indexing, and searching sound effects to weave into narration
Auto-maintained product walkthrough videos that update themselves from GitHub PRs. Claude + Playwright + ElevenLabs + ffmpeg.
Offline foley pipeline: long take-recording to named, axis-annotated sound atoms, then composed into game-ready variants. Companion to AnchorSFX.
Sound-effect, music-loop, and narration generator on AMD ROCm, NVIDIA CUDA, Mac MPS — ComfyUI + Stable Audio Open, driven by a one-command CLI. Sibling to pixelmon.
Physics-driven, controllable Foley for games — local-first, deterministic, and low-compute.
Homebrew tap for foley: brew install GH-Jaider/foley/foley
Hudka - local AI sound design from video. Generates licence-cleared sound effects and music on your own GPU. No cloud, no API keys, no per-render cost.
To associate your repository with the foley topic, visit your repo's landing page and select "manage topics."