Standard-Intelligence/hertz-dev
Base model for full-duplex conversational audio
View on index · View in 3D Map
Related repos
- open source audio model for expressive speech and voice cloning
- Trains speech recognition models in 24 hours for $12
- End-to-end speech-to-speech foundation model
- audio foundation model for understanding, generation, and conversation
- Audio language model for voice interactions
- speech recognition, synthesis, and audio tools for many platforms
- Upsamples audio to 48kHz
- Framework for real-time speaker diarization
- audio-driven video dubbing with unlimited length and accurate lip sync
- AI toolkit for speech enhancement, separation, super-resolution, and speaker extraction
