Image · Video · Audio ✕

Image · Video · Audio

big names · picking up speed
01
latent-spaces/brag
+1048 ★/day↗accelerating

The gap between 'it works' and 'anyone knows it works' is usually a launch video nobody wants to make — so this agent skill makes it for you.

★ 21.7k Python Coding Assistants · explained Feature
02
Vincentwei1021/video-shotcraft
+969 ★/day↗accelerating

It gives Claude Code and Codex a motion-design vocabulary—106 shot recipes, 161 previews, and a Remotion template—so they can direct cinematic product videos instead of generic slideshows.

★ 20.6k TypeScript Agents · explained Feature
04
jamiepine/voicebox
+368 ★/day↗accelerating

Voicebox is a local-first alternative to ElevenLabs and WisprFlow that clones voices, dictates anywhere, and gives AI agents a mouthpiece — all without shipping audio to the cloud.

★ 60.8k Python Image · Video · Audio · explained Feature
07
Wan-Video/Wan2.2
+56 ★/day↗accelerating

Wan2.2 is an open video generation suite that treats denoising timesteps like specialist jobs, scaling from a 5B model on an RTX 4090 up to a 14B MoE flagship that demands 80GB VRAM.

★ 18.7k Python Image · Video · Audio · explained
08
ATH-MaaS/Pixelle-Video
+59 ★/day↗accelerating

Pixelle-Video exists because producing a short video still requires scripting, generating assets, narrating, and editing; it automates all of that behind a single Web UI by orchestrating external AI services.

★ 30.2k Python Image · Video · Audio · explained
09
chidiwilliams/buzz
+60 ★/day↗accelerating

Buzz wraps OpenAI's Whisper in a cross-platform GUI that keeps your audio data local and adds features the raw model doesn't have.

★ 22.9k Python Image · Video · Audio · explained
11
ggml-org/whisper.cpp
+43 ★/day↗accelerating

A minimal C/C++ port of OpenAI’s Whisper built to transcribe speech locally on phones, browsers, and underclocked POWER9 boxes.

★ 55.3k C++ Image · Video · Audio · explained
12
m-bain/whisperX
+40 ★/day↗accelerating

OpenAI's Whisper is accurate but slow and timestamp-imprecise; WhisperX bolts on batching, forced phoneme alignment, and speaker diarization to fix that.

★ 25.4k Python Image · Video · Audio · explained
13
SYSTRAN/faster-whisper
+42 ★/day↗accelerating

A reimplementation of OpenAI's Whisper that trades the original inference engine for CTranslate2 and gains up to 4× speed without sacrificing accuracy.

★ 26.8k Python Inference · Serving · explained
14
sgl-project/sglang
+52 ★/day↗accelerating

SGLang exists to push low-latency, high-throughput inference for LLMs and multimodal models from a single GPU up to massive clusters.

★ 39k Python Inference · Serving · explained
15
Zeyi-Lin/HivisionIDPhotos
+22 ★/day↗accelerating

An open-source toolkit that turns casual selfies into compliant ID photos using offline AI matting and face detection.

★ 21.7k Python Computer Vision · explained
16
microsoft/VibeVoice
+168 ★/day↗accelerating

VibeVoice is a family of open-source speech models from Microsoft built to ingest, transcribe, and generate very long audio sessions—up to an hour—in a single pass.

★ 57.2k Python Image · Video · Audio · explained
17
chatfire-AI/huobao-drama
+59 ★/day↗accelerating

It turns a single sentence into a complete short drama by chaining LLMs, image generators, video models, and FFmpeg into one automated pipeline.

★ 17.6k TypeScript Domain Apps · explained
18
modelscope/FunASR
+15 ★/day↗accelerating

A Chinese speech toolkit that bundles ASR, diarization, emotion detection, and streaming into one MIT-licensed package.

★ 21.1k Python Image · Video · Audio · explained
19
invoke-ai/InvokeAI
+15 ★/day↗accelerating

It gives artists and professionals a local, node-based studio for Stable Diffusion, treating AI as a collaborator rather than an opaque generator.

★ 29.1k TypeScript Image · Video · Audio · explained
20
Huanshere/VideoLingo
+22 ★/day↗accelerating

It automates video transcription, translation, and dubbing while stubbornly insisting on single-line, human-readable subtitles.

★ 19.3k Python Domain Apps · explained
loading more…

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.