Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

Project for speech bubble

🇺🇦 Open Source Ukrainian Text-to-Speech datasets

Just a simple multimodal avatar interaction platform

A Docker-based OpenAI-compatible Text-to-Speech API server powered by Kyutai's TTS models with GPU acceleration support.

A voice-based AI chat interface built with Next.js and ElevenLabs. Start and stop real-time conversations with an animated UI that reflects agent status. Fully responsive and deployable via Vercel with environment-based agent configuration.

🇺🇦 Ukrainian RAD-TTS++ models (decoder + models with 3 voices) and HiFiGAN model

A voice-based AI chat interface built with Next.js and ElevenLabs. Start and stop real-time conversations with an animated UI that reflects agent status. Fully responsive and deployable via Vercel with environment-based agent configuration.

Enterprise-Grade Secure ASR Diarization Pipeline - HIPAA-compliant speech processing service combining automatic speech recognition with speaker diarization. Features modular architecture, comprehensive security, and production-ready deployment.

🎤 Power a fast, OpenAI-compatible Text-to-Speech API with GPU acceleration, supporting multiple audio formats and voice control in a complete Docker solution.