Voice Synthesis and Speech Recognition

10 repos

Tools and datasets for building text-to-speech (TTS), speech-to-text (STT), voice recognition, and intent recognition systems. The cluster spans Python libraries for audio processing and model training, TypeScript implementations for web-based voice applications, and C++ components for performance-critical speech processing. Repositories range from dataset generators and preprocessing utilities to complete TTS engines and voice application frameworks.

Python · 6
C++ · 2
Rust · 1
TypeScript · 1
tts ·23,492
stt ·23,492
intent-recognition ·22,070
voice-recognition ·22,070
voice ·22,070
ai ·1,318
llm ·1,311
live-translation ·1,280
chrome-extension ·1,280
electron ·1,280