语音

把语音转写从自建流水线降级成一次 pip install，代价是推理速度和显存要自己扛

本地跑完整语音流水线，替掉 ElevenLabs 的订阅和上传环节

用一分钟语音微调出可用音色的 TTS 训练推理一体工具，替代商业语音克隆 API 的自托管方案

SV2TTS 三阶段语音克隆的参考实现，用来把几秒音频变成可复用的说话人嵌入

无分词器的连续语音表示 TTS，用自然语言描述造音色、短音频克隆，绕开离散 token 那套流程

把文本直接变成语音、音乐和音效的生成模型，替代传统 TTS 流水线里的声学模型加声码器两段式

SV2TTS 的中文复现版，用 5 秒参考音频克隆音色，顶替从零训练 TTS 的整条链路

开源 TTS 里少数能同时做音色克隆、多说话人和标签式情绪控制的方案，顶替商用 TTS API

TypeScript 里把 agent、工作流和 eval 串成一套的框架，替代自己用 AI SDK 拼装编排层

单段参考音频做零样本音色克隆，情感和语速可调，顶替商用 TTS 的定制音色环节

用 LLM 做零样本多语言语音克隆，顶替传统 TTS 前端加声学模型的整条链路

把 EPUB/PDF 批量转成带章节元数据的有声书，用 50+ TTS 引擎在本地跑，替代 Audible/云端 TTS 的整本朗读流程

把视频翻译拆成 ASR、字幕翻译、TTS、合成四段流水线，每段可暂停人工校对，替代手工串四个工具

用流匹配做零样本音色克隆的 TTS 训练/推理框架，顶替传统 VITS 类方案

把歌词和风格提示先规划成乐谱再渲染成整首歌，需要可编辑中间产物时用它

用 Python 直接调用微软 Edge 在线 TTS 服务，替代本地跑模型或付费云 TTS 的轻量方案

端侧流式语音转写与意图识别库，替代 Whisper 在本地做低延迟语音前端

A fast, local neural text to speech system

把说话人日志拆成可组合的神经模块，直接顶替 Kaldi 那套 diarization 流水线

so-vits-svc fork with realtime support, improved interface and more features.

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具，使用你的音色或任意声音来录制音频

Generate audiobooks from e-books

vits2 backbone with multilingual-bert

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.

Towards Human-Sounding Speech

Silero Models: pre-trained text-to-speech models made embarrassingly simple

🎤 微软语音合成工具，使用 Electron + Vue + ElementPlus + Vite 构建。

Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI 视频翻译配音工具。

Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, websockets, optional readalong web UI

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

An Open Source text-to-speech system built by inverting Whisper.

这是一个Android系统TTS应用，内置微软演示接口，可自定义HTTP请求，可导入其他本地TTS引擎，以及根据中文双引号的简单旁白/对话识别朗读 ，还有自动重试，备用配置，文本替换等更多功能。

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

A simple, high-quality voice conversion tool focused on ease of use and performance.

A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

openctp提供CTP股票期权、中泰证券XTP、华鑫证券奇点TORA、东方证券OST、东方财富证券EMT、盈透证券TWS、易盛TAP、量投QDP等各通道的CTPAPI兼容接口，CTP程序可以无缝对接各股票柜台。openctp也提供了一套基于TTS交易系统的模拟环境，同样提供了CTPAPI兼容接口，不仅支持国内期货与期权全品种，也支持A股股票、基金、债券以及股票期权模拟交易，可以替代Simnow，为CTP量化交易开发者提供7x24可用的模拟环境。

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

TTS with kokoro and onnx runtime

Python library and CLI tool to interface with Google Translate's text-to-speech API

🤖️ Cross-platform AI language practice app （跨平台AI语言练习应用）

开源文本转语音工具，支持超长文本，多角色配音

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Controllable and fast Text-to-Speech for over 7000 languages!

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.

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices