HAKORADev/VODER

VODER brings together eight voice processing modes including speech-to-text, voice conversion, and music generation into one interface. It supports multi-speaker dialogue scripting, voice cloning from text or reference clips, and translation via TranslateGemma 12B, running entirely on your machine without a subscription.

View on index · View in 3D Map

Related repos

• open source text-to-speech model built by inverting Whisper, supports voice cloning and multilingual output
• open source toolkit for building real-time voice LLM apps and agents
• AI toolkit for speech recognition, transcription, and voice conversion
• AI Speech Recognition, Translation, and Dubbing Tool
• open-weight text-to-speech model for fast, natural voice synthesis
• Voice dictation for Linux with offline transcription
• Production-ready text-to-speech API with multiple voices and a real-time dashboard
• open-source text-to-speech with voice cloning and emotion control
• Offline voice recognition for Linux
• Offline speech recognition for 20+ languages