Python
Local ElevenLabs on Your Own Hardware with VoiceStudio
VoiceStudio brings local ElevenLabs-quality voice synthesis, cloning, and transcription to your own hardware—no cloud, no subscriptions, just open-source power.
#tts
7 projects Python
How to Set Up Fast Inference for Voice and Multimodal Models with SGLang-Omni
SGLang-Omni provides a specialized runtime for multi-stage inference of voice and multimodal models, handling the complex pipeline from audio encoding to speech synthesis.
Python
How to create videos from a single line of text using Pixelle-Video
Pixelle-Video is an engine for automating short video creation from a single text prompt. It generates MP4s with voiceover, subtitles, music, and AI visuals.
Python
How to Turn Any Book into a Multi-Voice Audio Production with Alexandria
Alexandria transforms any text into a multi-voice audio production using LLM analysis and neural speech synthesis. Here's how it works and whether it's worth trying.
C-plus-plus
How to Connect Unreal Engine with Modern Neural Networks Without the Extra Pain
UnrealGenAISupport is an open-source plugin that bridges Unreal Engine with modern LLMs like OpenAI, Claude, DeepSeek, and Gemini, featuring MCP support for editor control.
Python
IndexTTS2: When Synthesized Speech Sounds Truly Natural
IndexTTS2 is a next-generation open-source speech synthesis model with precise duration control and emotion separation for realistic voice generation.
21,665
Python
GPT-SoVITS: Clone a Voice in 5 Seconds
GPT-SoVITS is an open-source voice cloning solution that can synthesize speech from just 5 seconds of audio. Learn about its features and practical applications.
59,067