remsky/Kokoro-FastAPI
Dockerized FastAPI API for Kokoro-82M text-to-speech, supports CPUand GPU, handles speech requests
View on index · View in 3D Map
Related repos
- Real-time transcription using Faster-Whisper
- open-weight text-to-speech model for fast, natural voice synthesis
- Browser-based AI voice generator with WebGPU acceleration
- offline speech-to-text API for many languages, runs on lots of devices and platforms
- Production-ready text-to-speech API with multiple voices and a real-time dashboard
- AI-powered audio processing tool with speech recognition, translation, and TTS
- Offline voice recognition for Linux
- Live speech translation using OpenAI Realtime API
- real-time speech-to-speech AI model for natural conversations
- OpenAI-style text-to-speech API with voice cloning and web UI
