vocos 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
一个单一的 Gradio + React WebUI，为 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 和 Bark 提供扩展！
Vocos：缩小时间域和基于傅里叶的神经声码器之间的差距，实现高质量音频合成
A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation
🎙️ Arabic TTS models (Tacotron2, FastPitch)
🎙️ Arabic TTS models (FastPitch, Mixer-TTS) in the ONNX format — Python package for offline speech synthesis 🚀📦
Simplified installers for suno-ai/bark, musicgen, tortoise, RVC, demucs and vocos
用于TTS生成的Docker镜像一体化
A 6.25 Hz, 0.80 kbit/s streaming neural audio codec based on WavLM
High-fidelity speech synthesis for Ukrainian using modern neural networks.
Causal version of Vocos (neural vocoders for high-quality audio synthesis) with streaming implementation
Fast one-step Turkish TTS trained with drifting: streaming DiT, batched serving (256 concurrent requests, first audio in 52 ms on an RTX 5090), Triton kernels, and the training code
Edge-native real-time speech restoration & assistive communication engine for motor-speech impairments.