8 comments

  • singpolyma3 16 minutes ago
    Love this.

    It says MIT license but then readme has a separate section on prohibited use that maybe adds restrictions to make it nonfree? Not sure the legal implications here.

  • lukebechtel 20 minutes ago
    Nice!

    Just made it an MCP server so claude can tell me when it's done with something :)

    https://github.com/Marviel/speak_when_done

  • armcat 55 minutes ago
    Oh this is sweet, thanks for sharing! I've been a huge fan of Kokoro and event setup my own fully-local voice assistant [1]. Will definitely give Pocket TTS a go!

    [1] https://github.com/acatovic/ova

    • gropo 9 minutes ago
      Kokoro is better for tts by far

      For voice cloning, pocket tts is walled so I can't tell

    • amrrs 41 minutes ago
      Thanks for sharing your repo..looks super cool.. I'm planning to try out. Is it based on mlx or just hf transformers?
      • armcat 31 minutes ago
        Thank you, just transformers.
  • dust42 26 minutes ago
    Good quality but unfortunately it is single language English only.
    • phoronixrly 22 minutes ago
      I echo this. For a TTS system to be in any way useful outside the tiny population of the world that speaks exclusively English, it must be multilingual and dynamically switch between languages pretty much per word.

      Cool tech demo though!

  • tschellenbach 27 minutes ago
    It's cool how lightweight it is. Recently added support to Vision Agents for Pocket. https://github.com/GetStream/Vision-Agents/tree/main/plugins...
  • syntaxing 28 minutes ago
    Is there something similar for STT? I’m using whisper distill models and they work ok. Sometimes it gets what I say completely wrong.
  • GaggiX 1 hour ago
    I love that everyone is making their own TTS model as they are not as expensive as many other models to train. Also there are plenty of different architecture.

    Another recent example: https://github.com/supertone-inc/supertonic

  • snvzz 54 minutes ago
    Relative to AmigaOS translator.device + narrator.device, this sure seems bloated.