The database of free AI tools on GitHub

Fast, free voice assistant for your Mac. No API key: runs on your Claude Pro or Max plan. Sends background agents for big jobs, remembers you and learns your shortcuts. Hold ⌃⌥Space and talk.

Free, open-source offline voice dictation for Windows, macOS, and Linux. A Wispr Flow alternative with an AI assistant that can read your screen on request and answer questions.

Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time

From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model

Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identifies speakers offline, and writes summaries that fuse your no

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory

Input0 — A macOS voice input tool: hold a hotkey to record, release to transcribe locally via STT, refine with LLM, and auto-paste into the active text field.

Kokoro TTS for iOS and macOSX

wrong layout? keyboop. — free, open-source macOS layout switcher that doesn't break your clipboard. keyboop.com

macOS AI 语音输入工具，支持中文与中英混合识别、AI 文本整理、上下文格式匹配和本地优先。

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.

Browse WhatsApp chat exports offline with AI-powered voice transcription. Privacy-first desktop/web app with bookmarks, search, and statistics. Built with SvelteKit and Electron.

Fully Functional Voice Based Natural Language UI

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

Soprano-Factory: Train your own 2000x realtime text-to-speech model

AI music generation for live performance - Standalone (Ableton Link) + VST3/AU. 8 tracks, 9 AI models. It occasionally hallucinates. Not a song generator - you still have to do the work. Stay human.

VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control

Ukrainian TTS (text-to-speech) using ESPNET

Mila — native macOS local transcription app (whisper.cpp) with optional speaker diarization. Apache-2.0.

Auto transcribe tool based on whisper

Blazing fast whisper turbo for ASR (speech-to-text) tasks

Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fusion, Demucs stems, MIDI generate/notate, img > spectrogram >

[讯飞同传]免费平替——本地系统语音实时转写，国际会议、英文播客、生肉影视，屏幕浮窗、实时字幕、离线识别。

A multi-model local AI Voice Generator (TTS) studio. An open-source alternative to ElevenLabs and expensive online voice generators.

Local, private voice dictation for macOS

Text to speech package for Golang.

A text-to-speech and speech-to-text server compatible with the OpenAI API, supporting Whisper, FunASR, Bark, and CosyVoice backends.

On-device meeting transcriber for macOS — auto-records Teams/Zoom/Webex, transcribes & separates speakers locally. No cloud. Open-source alternative to Otter/Granola/Fireflies.