Open Issues Need Help
View All on GitHub Add Gemini models about 2 months ago
AI Summary: This feature request aims to integrate Google's Gemini models into the VTS application to enhance transcription and audio understanding capabilities. Users should be able to select a new Gemini/Google provider, choose Gemini models, and input their API key to utilize these highly-ranked models for voice dictation.
Complexity:
2/5
good first issue swift
j05u3/VTS
24
Transform your voice into text instantly with the power of OpenAI, Groq, and Deepgram APIs. Say goodbye to macOS dictation limitations and hello to lightning-fast, accurate transcription! ⚡️
Swift
#macos#stt#swift