jichengdu / cosyvoice

CosyVoice2-0.5B-Scalable Streaming Speech Synthesis with Large Language Models

  • Public
  • 1.3K runs
  • GitHub
  • Weights
  • Paper
  • License
Iterate in playground
Run with an API
Playground API Examples README Versions
  1. Author
    @jichengdu
    Version
    cuda12.1-python3.11-torch2.3.1-X64
    Commit
    4218d2ef814cb563cecfcedf3d3def6a882404bd

    4106862b

    Latest
  2. Author
    @jichengdu
    Version
    cuda12.1-python3.11-torch2.3.1-X64
    Commit
    362ba23268d9ed46dd9f1e64b37282a10dbb1f74

    6d5a4a99

  3. Author
    @jichengdu
    Version
    cuda12.1-python3.10-torch2.3.1-X64
    Commit
    41c5e8cd6d43d8fa018297973c045514e3886cb4

    abfd3445

  4. Author
    @jichengdu
    Version
    cuda12.1-python3.10-torch2.3.1-X64
    Commit
    41c5e8cd6d43d8fa018297973c045514e3886cb4

    066db45d

  5. Author
    @jichengdu
    Version
    cuda12.1-python3.10-torch2.3.1-X64
    Commit
    41c5e8cd6d43d8fa018297973c045514e3886cb4

    1cc525e1

  6. Author
    @jichengdu
    Version
    cuda12.1-python3.10-torch2.3.1-X64
    Commit
    41c5e8cd6d43d8fa018297973c045514e3886cb4

    f936bf2a