SenseVoice
FunAudioLLM
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
Media AutomationReview before use
8.6KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Search retrieves candidates across the registry and ranks a bounded shortlist by task fit. This count is matching candidates, not the registry total. No suitable match? Try a specific tool or task.
Results Β· βkorean-speechβ
17β32 / 82
More filters Β· 1
Results: 82
Vosk API
alphacep
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Media AutomationReview before use
15.1KGitHub
9.9KGitHub
Mlx Audio
Blaizzy
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
Media AutomationReview before use
7.4KGitHub
6.8KGitHub
6.4KGitHub
Wenet
wenet-e2e
Production First and Production Ready End-to-End Speech Recognition Toolkit
Media AutomationReview before use
5.2KGitHub
4.3KGitHub
Whisper Diarization
MahmoudAshraf97
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
5.6KGitHub
Wav2letter
flashlight
Facebook AI Research's Automatic Speech Recognition Toolkit
Media AutomationReview before use
6.4KGitHub
Dsnote
mkiol
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
Media AutomationReview before use
1.5KGitHub
Distil Whisper
huggingface
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Media AutomationReview before use
4.1KGitHub
Fun ASR
FunAudioLLM
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
Media AutomationReview before use
1.3KGitHub
1.6KGitHub
STT
coqui-ai
πΈSTT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
Media AutomationReview before use
2.6KGitHub
Sherpa Ncnn
k2-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,β¦
Media AutomationReview before use
1.7KGitHub
External platform skills
Browse external directory βOwner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
No external entries match this query.
Guides & comparisons
- AI agent skills library β
- Open source AI agent skills β
- Best Codex skills β
- Best AI agent skills for stock analysis β
- Best Codex skills for web scraping β
- Best Claude Code skills for PDF parsing β
- Best AI agent skills for football analytics β
- OpenAgentSkill vs skills.sh β
- OpenAgentSkill vs agentskills.io β