The database of free AI tools on GitHub
23,066 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.
345 repos · showing 31–60
Automatically transcribes and diarizes audio using OpenAI Whisper.
Dockerized FastAPI wrapper for text-to-speech with multi-speaker support and custom voicepacks.
离线语音识别转文字工具，支持多种语言和模型。
Real-time voice AI agent built on Ultravox LLM.
Generate high-quality multilingual speech on CPU for real-time voice cloning.
Converts text to speech in real-time with low latency.
AI-polished text from voice input in any app.
Converts voices with high quality and ease of use.
A high-performance C++ audio inference framework for TTS, STT, and voice conversion.
Keeps AI agents present and conversational in real-time.
Automatically synchronizes audio and text for speech-to-text applications.
Generate speech using Kokoro-TTS and ONNX runtime.
基于ChatTTS的文本转语音工具，支持流式输出和长音频生成。
Convert text to speech offline in Python.
实时生成2D视频数字人对话应用，无需GPU，适用于手机和网页。
Real-time voice AI with multimodal input for on-device speech recognition and text-to-speech.
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
Local speech-to-text for macOS on-device AI, fully private, optional cloud
Your tiny AI desktopet companion, built with Cortico 0 0)
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断
Automatically translates the text of a video based on a subtitle file, and then uses AI voice services to create a new dubbed & translated audio track where the speech is synced using the subtitle's t
Voice-to-text with push-to-talk for Wayland compositors
OBS plugin for local speech recognition and captioning using AI
Soprano: Instant, Ultra-Realistic Text-to-Speech
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.
A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text
AuK: An Open-Source Foundational Model for Speech Generation and Editing
Machine learning powered Karaoke app (with scores!)