usamaehsan/qwen3-tts-voice-design

Text-to-speech in a new voice designed from a text description (10 languages). Qwen3-TTS VoiceDesign, Apache-2.0. No audio input, no cloning; descriptions that name a real person are refused.

Public
14 runs
  1. Author
    @usamaehsan
    Version
    cuda12.4-python3.11-torch2.6.0-X64
    Commit
    ad40a08da114637a031125d4546de17e34892f17

    6461c4dc

    Latest
  2. Author
    @usamaehsan
    Version
    cuda12.4-python3.11-torch2.6.0-X64
    Commit
    ad40a08da114637a031125d4546de17e34892f17