search

eliranwong / letmedoit

An advanced AI assistant that leverages the capabilities of ChatGPT API, Gemini Pro, AutoGen, and open-source LLMs, enabling it both to engage in conversations and to execute computing tasks on local devices.
https://letmedoit.ai
GNU General Public License v3.0
112 stars 24 forks source link

Support voice entry / typing with openai whisper model #43

Closed eliranwong closed 5 months ago

eliranwong commented 5 months ago

Support voice entry / typing with openai whisper model

eliranwong commented 5 months ago

doable, but slow for non-English languages, prefer Google speech-to-text for non-English entry

eliranwong commented 5 months ago

will support it via manual change of config.py

eliranwong commented 5 months ago

Key binding "Esc+F" to change voice typing configurations

voice_typing_config_1

eliranwong commented 5 months ago

done https://github.com/eliranwong/letmedoit/commit/085b48a3a0de429d359c39eeccfa32ab8ce18a32