Skip to content

Features

Jump to bottom
Mylo edited this page Jun 16, 2023 · 1 revision

Features (including planned)

  • 🔊 Text-to-audio
    • 🗣 Text-to-speech
      • 🐶 Bark
        • 🗣 Speech generation
        • 🧬 Voice cloning
        • 🤣 Disable stopping token option to let the AI decide how it wants to continue
    • 🎵 AudioLDM text-to-audio generation
    • 🎵 AudioCraft text-to-audio generation
  • 🔊 Audio-to-audio
    • 🐶 Bark audio-to-audio using a custom quantizer to deconstruct audio for bark input
    • 😎 RVC (retrieval based voice conversion)
  • 🎤 Automatic-speech-recognition
Clone this wiki locally