> 发现和探索全球最新的AI工具
Bark is an open-source text-to-audio model by Suno AI that can generate highly realistic speech, music, background noise, and sound effects from text prompts. It supports multiple languages and voice styles and is available on GitHub for self-hosting.
Tortoise TTS is an open-source multi-voice text-to-speech model known for producing highly expressive and natural-sounding speech with voice cloning capabilities from audio references. It prioritizes audio quality over speed and is used in research and creative audio applications.
LiveKit is an open-source WebRTC infrastructure platform for building real-time audio, video, and data applications at scale, commonly used for building AI voice agents and multi-party video applications. It provides server-side media processing, AI agent integration, and scalable media routing.