Best Voice AI AI skills

Opencode is an open source coding agent that assists with coding tasks using voice commands and AI.

Unsloth allows founders to train and run open AI models like Gemma 4, Qwen3.6, DeepSeek, and gpt-oss locally using a web UI

Airi is a self-hosted AI companion that allows for real-time voice chat, Minecraft, and Factorio gameplay, bringing virtual characters into your world.

Meetily is an AI meeting assistant that provides fast and accurate live transcription, speaker diarization, and meeting summarization, all while maintaining privacy through 100% local processing

cmux provides a macOS terminal with vertical tabs and notifications for AI coding agents, enhancing the coding experience for founders using AI coding tools

Opencode is an open source coding agent that assists with coding tasks using voice commands and AI.

Unsloth allows founders to train and run open AI models like Gemma 4, Qwen3.6, DeepSeek, and gpt-oss locally using a web UI

Airi is a self-hosted AI companion that allows for real-time voice chat, Minecraft, and Factorio gameplay, bringing virtual characters into your world.

Meetily is an AI meeting assistant that provides fast and accurate live transcription, speaker diarization, and meeting summarization, all while maintaining privacy through 100% local processing

cmux provides a macOS terminal with vertical tabs and notifications for AI coding agents, enhancing the coding experience for founders using AI coding tools

Pydantic-ai provides a framework for building AI agents using Pydantic, allowing founders to create structured and scalable AI models

Speech is a scalable generative AI framework for building Automatic Speech Recognition and Text-to-Speech systems using Large Language Models and Multimodal techniques.

Run various large language models (LLMs) with a single unified API, allowing you to easily switch between models by changing just one line of code.

AI‑powered one‑click pipeline that writes scripts, generates voice‑overs, creates visuals, assembles short videos and auto‑posts them to Chinese short‑video platforms.

FunClip transcribes videos, generates subtitles, and clips them using AI, all through a simple, local interface.

Turn long-form YouTube videos into viral 9:16 shorts using LLM highlight detection, Whisper transcription, and auto vertical cropping

Openless is a free voice input tool that allows you to get polished text in any app by holding a key, speaking, and releasing, with AI-polished text appearing at your cursor.

Patter gives your AI agent a phone number, allowing users to interact with your AI via voice calls using a simple, open-source voice-AI SDK

Viral-clips-crew is a CrewAI powered video editing assistant that helps users edit videos using voice commands and AI-powered editing tools.

Local voice AI powered by llama-cpp, Kokoro, Nemotron STT, and LiveKit allows founders to integrate voice AI into their applications without relying on cloud services.

QVAC allows founders to run AI applications privately and locally on various platforms, including Linux, macOS, Windows, Android, and iOS, for building cross-platform AI tools.

Opentypeless provides open-source voice typing for macOS, Windows, and Linux, allowing founders to achieve hands-free productivity by speaking naturally and getting polished text in any app.

PreenCut is a tool that uses AI to instantly retrieve and clip specific parts of videos, allowing founders to quickly access and share relevant video content.

VideoHighlighter is an open-source, local AI video analyzer that automatically detects highlights, scenes, actions, objects, and generates subtitles for videos using visual and audio analysis.

This tool provides a reference implementation of an end-to-end voice agent built using the NVIDIA Nemotron models, allowing founders to integrate voice AI into their startup