The database of free AI tools on GitHub
23,020 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.
346 repos · showing 301–330
A class for generating realistic audio (TTS) for podcasts and dialogues.
Local Audio Transcription Tool
Local voice cloning + SRT-driven web presentations. Two installable Agent skills: script → voice → motion.
Native macOS screen recorder with teleprompter, camera overlay, system audio capture, 4K export, and AI breath cuts.
🚀 Open-source project for creating high-quality AI TTS-narrated audiobooks at home using models like Zonos, Kokoro-82M, or services like Deepgram and Eleven Labs. Tested on Apple Silicon M1 (32GB RAM
Open-source macOS dictation that turns speech into polished text in the app you're already using. Powered by AssemblyAI.
Streaming Persian (Farsi) speech recognition: fine-tuning NVIDIA Nemotron 3.5 ASR streaming. Data prep, training, evaluation, inference.
MacOS desktop speech-to-text. Private, offline, open-source. Choose your own STT (Speech to Text) providers, and LLM providers that polish your mumbles. Bind any prompt templates with any shorcuts
轻阅 — 开源本地优先的全格式电子书阅读器 | EPUB/MOBI/AZW3/FB2/PDF/TXT · 听书 · OPDS/arXiv/Calibre 书源 · Tauri 2 + Vue 3
Free, open-source Whisper desktop app — 100% offline speech-to-text for Windows, macOS & Linux. No cloud, no subscription.
Single-file C++ TTS runtime for Pocket TTS with ONNX Runtime — voice cloning, streaming, HTTP server, FFI C API
Official Repo for "AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach"
Pure-MLX speech synthesis, voice cloning, dialogue, sound-effects, and ASR for Apple Silicon: Fish S2 Pro, VibeVoice, LongCat, MOSS, Step-Audio, Cohere ASR.
Mac-native dictation that just works – lives in the notch, zero setup, free forever
go-speech 基于 Golang + ONNX 构建的轻量语音库，支持 TTS（文本转语音）与 ASR（语音转文字）。已集成 MeloTTS、Piper、达摩院 Paraformer 架构模型、Whisper 模型。
Generate AI music from your terminal — Suno v5.5 with tags, exclude, vocal control, and all generation features
Real-time on-device speech translation for macOS. Silero VAD + Qwen3-ASR-1.7B + Qwen3.5 (MLX) on Apple Silicon. No cloud, no API keys, no telemetry.
Optimized Retrieval-based Voice Conversion WebUI for Apple Silicon Macs (M1/M2/M3). Real-time, high-quality voice conversion with an easy web interface. All models included!
Push-to-talk voice typing for your terminal. Local Whisper, cross-platform.
CosyVoice inference in C/C++
EchoInStone is an audio processing tool that transcribes, diarizes, and aligns speaker segments from audio files, prioritizing accuracy and reliability.
ESP32-P4 dynamic RISC-V compiler - faster iteration (1-2s vs 30-60s firmware rebuild) | Native performance, zero interpreter overhead | NumPy integration with automatic type conversion & memory manag
Simple, Fast and Efficient Speech-to-Text API Service based on Qwen3-ASR. 简单快速高效的语音识别API服务
Real-time YouTube Live Chat Text-to-Speech (TTS) using ElevenLabs AI voices
Python-based Telegram transcriber bot utilizing local Whisper models & yt-dlp
macOS menu bar app providing a local HTTP server compatible with the OpenAI Whisper API for fast and private audio transcription.
Sample project for F5-TTS using MLX Swift
Voice input that transcribes what you said, grounded in what's on your screen. macOS, Windows, Android, iOS.
CLI for audio, video, and text transcription with ASR providers and LLM-powered summarization via local or cloud backends.
TalkiTo lets developers interact with AI systems through speech across multiple channels (terminal, API, phone). It can be used as both a command-line tool and a Python library.