open-mmlab/Amphion
Amphion: Audio, music, and speech generation toolkit
View on index · View in 3D Map
Related repos
- open source audio model for expressive speech and voice cloning
- Web-based audio and waveform editor
- speech interface tools for audio comprehension and generation
- Generates songs with vocals and instrumentals from text prompts or audio references
- Voice dictation for any application on a computer
- open-source model for speech-to-speech and audio understanding
- open-source model for generating music from text or audio inputs
- speech-to-speech pipeline using open models for voice detection, transcription, language modeling, and speech synthesis
- Synthesizes speech without tokenizers
