AI Agent Skills

💬Speech recognition for your React app

The official repository of the Eesen project

Descriptive Deep Learning

从一个想法或一份文案，做出一条完整的「档案剪贴」风格短片——满幅象牙纸、单色印刷黑白、单一暗砖红，镜头用 MiniMax H3 首尾帧驱动，配音用 Fish Audio，成片用 ffmpeg 合成。当用户想用档案剪贴/编辑设计/纸质拼贴风格做视频，或要把一段文案、一个选题、一条新闻做成解说短片时使用。包含环境安装检查、拆故事拆画面拆节奏…

Stephanie is an open-source platform built specifically for voice-controlled applications as well as to automate daily tasks imitating much of an virtual assistant's wor…

Project that allows one to use a microphone with OpenAI whisper.

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

🎤 The easiest way to transcribe audio in Swift

A command-line application to convert images, PDFs, and audio files to text using Apple's APIs

Running speech to text model (whisper.cpp) in Unity3d on your local machine.

Chinese text normalization for speech processing

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

Transcribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wizper, Scribe, xAI STT), supported formats (wav/flac/m4a/aac/…

Call POST /chat/completions on Venice. Covers the OpenAI-compatible request shape, Venice-only venice_parameters (web search, E2EE, characters, thinking control, X searc…

Generate and transcribe videos via Venice. Covers the async /video/quote + /video/queue + /video/retrieve + /video/complete loop, text-to-video, image-to-video, video-to…