Voice

Gen Audio

• Stability AI
  • Stable Audio
  • HF: https://huggingface.co/stabilityai/stable-audio-open-1.0 
  • Stability AI Launches Open-Source Model to Generate Audio (itsfoss.com)
• FunAudioLLM - Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
  • GitHub: https://github.com/FunAudioLLM 

Instant voice cloning

• OpenVoice

Text to Speech (TTS)

• ChatTTS
  • 6drf21e/ChatTTS_colab: 🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。 (github.com)
• MARS 5
  • GitHub: https://github.com/Camb-ai/MARS5-TTS 
  • HF: https://huggingface.co/CAMB-AI/MARS5-TTS 
• edge-tts - An Python module that allows you to use Microsoft Edge's online text-to-speech service from within your Python code or using the provided edge-tts or edge-playback command.
  • GitHub: https://github.com/rany2/edge-tts 
• fish-speech
  • GitHub: https://github.com/fishaudio/fish-speech 
• 雅婷智慧 (台灣人工智慧實驗室)
  • https://github.com/TaiwanAILabs-Yating  
• Qwen-TTS (通義千問 TTS)
  • Qwen3-TTS vs ElevenLabs : Voice Cloning & Real-Time Streaming - Geeky Gadgets
• VibeVoice (Microsoft)
  • HF: https://huggingface.co/microsoft/VibeVoice-1.5B 
• Pocket TTS 

ASR - Automatic Speech Recognition

• FrogBase - OpenAI 影片逐字稿生成與翻譯
• InstantID - 文字生成圖像 AI，個人風格頭像生成
• WhisperDesktop - 影片生成字幕逐字稿，For Windows Only
  • [Video] 免安裝版Whisper　無須安裝便可使用｜硬體需求大幅降低｜使用Ｃ＋＋編寫　無須額外安裝函式庫
• OpenAI Whisper
• Whisper WebUI - 網頁操作介面
• WhisperX - 比 whisper large-v2 快 70 倍
• Fast Whisper - 比 OpenAI Whisper 的速度快，資源消耗較低
• Vosk - Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
• Handy - A free, open source, and extensible speech-to-text application that works completely offline.

MTK Breeze 3

聯發創新基地（MediaTek Research）發表全新 MediaTek Research Breeze 3（後略 MR Breeze 3）系列，包含台語語音辨識模型 Breeze ASR 26、台語語音合成模型 BreezyVoice 26，以及專為台灣設計的 AI 內容安全防護模型 Breeze Guard 26。

MediaTek Research Breeze 3：讓 AI 聽懂台語、說出台味、守護台灣