VoiceSissy (Speech-to-Text-to-Speech TTS STT)

VoiceSissy is easy-to-use select-to-speech tool as well as text-to-speech (TTS) AND speech-to-text (STT) text editor.

- Turn your speech into machine voiced (Realtime Speech-to-Text-to-Speech)
- Transcribe your speech in text edtor (STT Transcriber Editor)
- Read selected text on any webpage (Text segmentation and TTS)
- Read your text as you write (TTS Talk Editor)

Originally this software was developed for VOICEVOX but you can use it with Chrome's built-in voice synthesizers. VOICEVOX produces human-quality tech-to-speech (TTS)  deep learning technology to human-quality TTS in Japanes, and it's free :)

VoiceSissy supports the following TTS engine for now.

- Built-in Voice Synthesis
    - Google Chrome built-ins
        - English, Spanish, French, German, Japanese etc...
    - Operation System built-ins
        - Microsoft voices (on Windows)
        - Apple voices (on macOS)
- VOICEVOX
    - Shikoku Metan (Japanese)
    - Zundamon (Japanese)
- Bouyomi-Chan (via WebSocket plugin)


Usage:

1. Open https://voicevox.hiroshiba.jp/ and setup VOICEVOX.
2. Run VOICEVOX on your machine.
3. Select any text on your browser, right click, then select "VoiceSissy : Read".
4. Browser will read out the selected text.


Support:

Throw any complaint or idea to my twitter, I might consider writing code for it :)
http://twitter.com/higon/