# Tencent-Hunyuan/HunyuanVideo-Foley

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

Repository: https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley
Canonical: https://ross.abutalabs.com/products/hunyuanvideo-foley
Homepage: https://hunyuan.tencent.com/video/zh?tabIndex=0
Language: Python
License: NOASSERTION
License Family: other
Topics: foley-art, foley-sound-synthesis, text-to-audio, text-to-video, tta, video-to-audio, aigc-audio, text-video-to-audio
Last push: 2025-09-28T17:48:49+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 44, release rhythm 35, longevity 27
- inputs: {"age_days": 383, "days_push": 339, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1052, forks 103 (observed 2026-08-28T04:03:23.506412+00:00)

## What it is
HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan that generates high-fidelity Foley sound effects synchronized with video, conditioned on video and optional text prompts. It provides inference code, pretrained model weights (including an XL variant with VRAM offloading), and a Hugging Face demo.

## Use cases
- generate foley sound effects for a video clip
- add synchronized audio to silent footage with AI
- text and video to audio generation
- create sound effects for video content automatically
- generate high-fidelity audio tracks matching visual events
- dub sound effects onto AI-generated videos

## When to choose
- you need AI-generated sound effects synced to video content
- you want a state-of-the-art video-to-audio foley model with open weights
- you are building video post-production or AIGC audio pipelines in Python

## When to avoid
- you need general-purpose text-to-speech or music generation
- you need a lightweight CPU-only audio tool
- you require a permissive commercial license without review (license is custom)

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, machine-learning, deep-learning, video-processing, llm-inference
- domain: artificial-intelligence, machine-learning, media
- platform: python, cross-platform
- tags: foley, text-to-audio, video-to-audio, diffusion-model, aigc-audio, sound-effect-generation, multimodal, audio, video, gpu, linux

## Member repositories
- Tencent-Hunyuan/HunyuanVideo-Foley (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.506412+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:59:41.315379+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley (fetched 2026-08-28T04:03:23.506412+00:00, sha 1fa613603a9e)
  - homepage: https://hunyuan.tencent.com/video/zh?tabIndex=0 (fetched 2026-08-29T13:01:14.799620+00:00, sha e9ec7b1723ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.