zunda-ASMR

zunda-ASMR is speech to text to speech by voicevox(+α) and whisper .

voicevox(+α) + whisper による speech to text to speech(STS)

intro.mp4

Install

⚠️現在python=3.8限定⚠️

pip install git+https://github.com/OhkuboSGMS/zunda-ASMR 

Run

zunda --audio_files <audio_file> --output <output_file_name>

GUI

flet zunda_w\gui\__main__.py

Author

Okubo Shigemasa

• Twitter Alt_Shift_N
• Github OhkuboSGMS

License

Distributed under the MIT License. See LICENSE for more information.

Engines

name	URL
VOICEVOX	https://github.com/VOICEVOX/voicevox_engine

API List

• HackMD API - https://hackmd.io/@hackmd-api/developer-portal
• Hatena API - https://developer.hatena.ne.jp/ja/documents/blog/apis/atom
• OpenAI API - https://beta.openai.com/docs/api-reference
• Voicevox Engine - https://voicevox.github.io/voicevox_engine/api/
• Claude AI - https://claude.ai/docs/