kokoro-82m 开源项目推荐（51 个）

denizsafak /abogen

从 EPUB、PDF 和文本生成带同步字幕的有声书。

remsky /Kokoro-FastAPI

用于 Kokoro-82M 文本转语音的 Docker 化 OpenAI 兼容封装，基于 PyTorch 支持多平台 CPU、AMD、NVIDIA GPU；支持多说话人、克隆调优、字幕时间戳、SSML、可选的跟读 Web UI

eduardolat /kokoro-web

Kokoro Web：免费的 AI 文本转语音，可在线使用或自托管，兼容 OpenAI！

CodeBySonu95 /VoxSherpa-TTS

🎙️ VoxSherpa Android 离线神经文本转语音引擎 ⚡ Sherpa-ONNX 支持🔊的自然语音合成 📱 完全离线处理 🚀 无云 • 无限制

qorvyx /kokorodoki

Natural-sounding Text-to-Speech App that fits anywhere. Fast, Real-Time and flexible.

pguso /voice-agents-from-scratch

From-scratch voice agents in Python: end-to-end speech pipelines, runnable chapters, and a small shared library. Local models, explicit streaming behavior.

jashdubal /atten

Local text-to-speech app for windows + mac

remsky /inno-kokoro

Zero-shot clone-tuner for Kokoro-82M. Generate stock-compatible custom voice packs from 5-seconds of reference audio in less than 1-second

usrbinbrain /kokoro-tts-container

一个用于运行Kokoro文本转语音引擎v.1的Docker容器，提供高质量的语音合成

aparsoft /kokoro-mcp-server

TTS toolkit built on Kokoro-82M with librosa audio enhancement, MCP server for Claude/Cursor, CLI & Python API. Free & open-source for YouTube creators.

willepalmberg /SimplerKokoro

A Python package that makes it easy to use the Kokoro voice synthesis library.

pguso /kokoro

A lightweight, offline Rust inference library for Kokoro TTS - an 82M-parameter open-weights text-to-speech model.

pguso /speechfony

Speechfony is a local-first desktop app that reads your PDFs aloud and turns them into audiobooks - fully offline, powered by Kokoro 82M and local LLMs via llama.cpp.

eujuliu /anki-deck-generator

This tool allows users to create Anki cards with words, meanings, examples, and IPA pronunciations, and convert text to speech for audio files.

arkodeepsen /kokoro

Production-ready RunPod serverless endpoint for Kokoro TTS. Features high-quality text-to-speech, voice mixing, word-level timestamps, and phoneme generation. Optimized for fast cold starts and auto-scaling.

wfloat /wfloat

On-device AI SDKs for Web, React Native, and Python.

kavishannip /whisper-ai-psychiatric-RAG-gemma3-finetuned

An advanced AI mental health assistant that combines voice interaction, fine-tuned psychology models, and intelligent knowledge retrieval to provide comprehensive psychological support.

solveditnpc /Kokoro-82M-audiobooks

create audio books from pdfs with one click , available on windows , linux, mac

47thtechcorner /RayCodes_KokoroVoiceCloner

Kokoro 82M Just Got Voice Cloning — In Under 1 Second! Zero-shot voice cloning pipeline using Kokoro-82M and inno-kokoro tuner.

speech-central /sc-voices-android

Open-source Android text-to-speech engine powered by Kokoro-82M, delivering natural-sounding AI voices with on-device GPU acceleration.