No visual example yet
Explore the skillSenseVoice
FunAudioLLM
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
OPENAGENTSKILL / DIRECTORY
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
6 Skills
Results: 6
Files returned by OpenAgentSkill since Oct 14, 2026. Signed-in accounts only; repeat downloads of the same Skill count once per UTC day. Excludes source-site downloads, command copies and installs. Counts may take 5 minutes to update.
No visual example yet
Explore the skillFunAudioLLM
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
No visual example yet
Explore the skillBreakthrough
:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.
No visual example yet
Explore the skillPicovoice
On-device wake word detection powered by deep learning
No visual example yet
Explore the skillspotify
A lightweight yet powerful audio-to-MIDI converter with pitch bend detection
No visual example yet
Explore the skillk2-fsa
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows,…
No visual example yet
Explore the skillOrchestra-Research
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic…