Trending repositories: speech-synthesis
6 tracked repositories tagged with speech-synthesis, ordered by stars. Use the topic filters below to narrow further.
6 of 6 repositories
OpenBMB/VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
AI summary: A highly efficient, tokenizer-free Text-to-Speech (TTS) generation model.
35,013ai-mlPythonApache-2.0supertone-inc/supertonic
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
AI summary: A blazing-fast, 99M-parameter multilingual text-to-speech engine optimized for on-device inference.
13,606ai-mlSwiftMITQwenLM/Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
AI summary: A highly natural, multilingual Text-to-Speech model from the Qwen team, capable of zero-shot voice cloning.
12,836ai-mlPythonApache-2.0abus-aikorea/voice-pro
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
AI summary: Comprehensive Gradio WebUI for advanced audio processing, featuring zero-shot voice cloning, transcription, and dubbing.
12,072ai-mlPythonGPL-3.0huggingface/speech-to-speech
Build local voice agents with open-source models
AI summary: A modular, open-source voice pipeline for building real-time, low-latency conversational AI agents.
11,547ai-mlPythonApache-2.0Blaizzy/mlx-audio
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
AI summary: High-performance audio processing library optimized for Apple Silicon via the MLX framework.
7,688ai-mlPythonMIT