LLaSA Training alternatives for AI agents.

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

A talking LLM that runs on your own computer without needing the internet.

[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

The code for the bark-voicecloning model. Training and inference.

Implementation of F5-TTS in MLX

Run Orpheus 3B Locally With LM Studio

unofficial vits2-TTS implementation in pytorch

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300M) TTS. OpenAI Realtime API compatible. Voice cloning, barge-in, ~9× realtime on a 4090. Apache 2.0.

Simple Python script to interact with the TikTok TTS API

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

A lightweight, offline Android Text-to-Speech (TTS) engine enabling seamless system-wide voice cloning and high-fidelity text reading. / 运行在安卓本地的轻量级文字转语音 (TTS) 引擎，支持离线发音人提取、零门槛音色克隆与双擎系统级全局听书。

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.