Hyper-fast, local, high-quality TTS based on Kokoro-82M. PySide6 GUI included.
Run local TTS engines on Google Colab as an OpenAI-compatible /v1/audio/speech endpoint for quick evaluation.
A Python package that makes it easy to use the Kokoro voice synthesis library.
Local TTS pipeline for converting text to audio and streaming to devices
Privacy-first, browser-based text-to-speech studio powered by Kokoro. Generate and download natural speech locally with no backend or data collection.
Local TTS server with Piper engine, in-memory processing, and 11 voice modes.
VOX-1 Audiobook Maker is a local, GPU-accelerated studio for creating professional-quality audiobooks. Powered by OmniVoice TTS, it allows users to design voices from text descriptions or clone narrators from short audio samples.
Rust-native voice agents for Node.js — WebRTC, VAD, barge-in, and speech events. Free on-device STT+TTS via Sherpa-ONNX; cloud vendors optional. Your LLM stays in TypeScript.
TTS Fast Web，一个简单优雅的本地文字转语音的前端与API接口。A localized, cross-platform, multi-language supported, OpenAI API format compatible, full-stack, ready-to-deploy TTS (Text to Speech) model
Offline Chinese and English local TTS CLI/API with sherpa-onnx, Matcha TTS, Docker, and Codex/Obsidian hooks.
🐱 Kitten TTS Studio using local onnx models TTS Offline
Give Claude Code a voice — local, bilingual (ES/EN) text-to-speech that reads responses aloud as they stream. Kokoro ONNX, no API keys, no cloud.
Turn Obsidian notes into private, natural offline speech.
Let there be voice for coding agents.
Ultra-low latency AI Spanish tutor using on-device STT (Moonshine), VAD (Silero), and TTS (Piper). Built with Flutter, BLoC, and Clean Architecture, featuring Groq Llama 3.3 with Gemini fallback.
HAL 9000 voice cloning with Qwen3-TTS streaming - OpenAI-compatible REST API
Privacy-first Codex Skill for authorized local voice cloning with CosyVoice2, pronunciation control, prosody guidance, and QA—no per-call API fee.
Local voice I/O for Claude Code and LLM workflows. Kokoro TTS reads every response aloud, faster-whisper handles voice input. No API keys, no cloud, no subscriptions. Accessibility-first.
Browser extension that reads web pages aloud using locally run TTS.
Add a description, image, and links to the local-tts topic page so that developers can more easily learn about it.
To associate your repository with the local-tts topic, visit your repo's landing page and select "manage topics."