blablabla 0.0.16

Project Blablabla: Conversational AI for the Modern Era

Imagine a world where interacting with artificial intelligence is as natural as chatting with a friend 🤖. Welcome to Blablabla, a pioneering voice-activated chat interface that's taking the first step towards making human-AI conversations a reality 💬.

Current Focus: Live Transcription

We're excited to announce that our platform now offers live transcription capabilities, allowing users to effortlessly convert spoken words into written text in real-time 💻. This innovative feature sets the stage for a more intuitive and seamless interaction with artificial intelligence 🎉.

Live Transcription Features

Accurate and Instantaneous: Our platform provides highly accurate and instantaneous transcription of spoken words, empowering users to focus on the conversation rather than note-taking 📝. Real-time Feedback: Get immediate feedback on your conversations, enabling more effective communication and collaboration 📊.

Running the tool

For now, just running using python: python -c "import blablabla; blablabla.start_all()"

Future Roadmap

While live transcription is just the beginning, we envision a future where Blablabla enables conversational interactions with Large Language Models (LLMs) and other AI systems 🔜. Our ultimate goal is to create a platform that allows humans to engage with AI in a natural, intuitive, and conversational way 💡 that you can control !

[ ] Enable faster transcription by avoiding encoding multiple time the same audio file. [ ] Enabling speculative decoding for repeated transcription [ ] Integrate with other LLM to provide question answer from speech

Inspiration:

This project was inspired by whisper_streaming and whisper-writer.