search

Bin-Huang / chatbox

User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)
https://chatboxai.app
GNU General Public License v3.0
22.99k stars 2.29k forks source link

[Feature] Speech-to-Text Functionality in ChatBox #1629

Open udaylunawat opened 5 days ago

udaylunawat commented 5 days ago

Problem Description: Currently, ChatBox lacks a speech-to-text feature, which limits accessibility and efficiency for users who prefer or need to dictate their messages instead of typing. For someone like me, this feature is incredibly useful and time-saving, as I often use it in apps like ChatGPT’s mobile and desktop versions. Having a similar capability in ChatBox would enhance usability and make it more versatile.

Proposed Solution: Introduce a microphone button in ChatBox that allows users to convert speech to text seamlessly. This feature could use OpenAI’s Whisper or a similar advanced transcription model, rather than relying on the native macOS or iOS speech-to-text capabilities. This ensures better accuracy and consistent performance across platforms, as seen in ChatGPT apps.

Additional Context: This feature is particularly helpful for users who multitask or prefer speaking over typing, and it would align ChatBox with other modern apps that prioritize accessibility. Implementing this would not only improve user experience but also make ChatBox a more competitive and user-friendly tool.

Thank you for considering this feature!

udaylunawat commented 5 days ago

My aim is to use openrouter with chatbox, and use multiple APIs like claude and chatgpt without paying more than $20/month. Speech to text feature from OpenAI is something that I miss a lot!