ekwek1/soprano-factory
Trains text-to-speech models with 2000x realtime generation on GPU
View on index · View in 3D Map
Related repos
- open-weight text-to-speech model for fast, natural voice synthesis
- Real-time transcription using Faster-Whisper
- Text-to-speech on CPUs with voice cloning
- Browser-based AI voice generator with WebGPU acceleration
- Production-ready text-to-speech API with multiple voices and a real-time dashboard
- Text-to-speech engine for long-form audio
- Listens to a microphone and sends speech-to-text transcripts in real time
- Trains speech recognition models in 24 hours for $12
- Text-to-speech library with advanced models in 17 languages (legacy models in 1100+), and tools for custom voice training
- AI model for zero-shot speech editing and text-to-speech
