Skip to content

krunixbase-dev/transcribe-assistant

📘 Description

transcribe-assistant is an offline, low-latency (~250 ms) real-time speech-to-text engine built for automation workflows, assistants, accessibility tools and privacy‑sensitive environments.

It uses local Faster‑Whisper inference, provides zero cloud dependencies, supports session recording, modular backend architecture, and includes a deterministic PRO version for compliance‑ready use cases.


🚀 Overview

transcribe-assistant is a fast, offline, real-time transcription engine built for:

  • automation workflows
  • assistants and agents
  • accessibility
  • offline environments
  • low-latency speech-to-text

This is the public version (non-deterministic).
The deterministic PRO version is part of the Krunixbase ecosystem.


✨ Features

  • ~250 ms latency
  • offline inference
  • Faster-Whisper backend
  • streaming transcription
  • session recording
  • export to TXT / JSON
  • CLI + Python API

🏗 Architecture

See full architecture here:
ARCHITECTURE.md


🛠 Installation

pip install -r requirements.txt
python main.py

📡 API

See API documentation:
API.md


🗺 Roadmap

See full roadmap:
ROADMAP.md


💰 Pricing

See pricing model:
PRICING.md


📄 License

MIT License.


About

Offline, low‑latency (~250 ms) speech‑to‑text engine with local Faster‑Whisper, zero telemetry, modular architecture and deterministic PRO version.

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages