chidiwilliams/buzz

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

What it solves

Buzz provides a way to transcribe and translate audio and video files offline on a personal computer, removing the need for cloud-based services. It also enables real-time transcription for live events and presentations.

How it works

It is powered by OpenAI's Whisper model and supports multiple backends for hardware acceleration, including CUDA for Nvidia GPUs, Apple Silicon for Macs, and Vulkan for a wide range of other GPUs. It can process local files, YouTube links, or live microphone input, and can utilize speech separation to improve accuracy in noisy environments.

Who it’s for

It is designed for users who need private, offline transcription and translation, as well as presenters who require live captioning for their audiences.

Highlights

  • Versatile Input: Supports audio/video files, YouTube links, and live microphone input.
  • Hardware Optimized: Acceleration for Nvidia, Apple Silicon, and Vulkan-compatible GPUs.
  • Advanced Tools: Includes speaker identification, speech separation, and a transcription viewer with playback controls.
  • Automation: Features a watch folder for automatic processing and a CLI for scripting.
  • Extensible: Includes a plugin system for tasks like AI summary generation.

Related

  • Project
    thewh1teagle/vibe

    A private, offline audio and video transcription tool that uses AI models like Whisper to convert speech to text locally on your device.

  • Project
    jasoncheng7115/jt-live-whisper

    A fully local AI toolkit for real-time speech transcription, translation, and meeting summarization that works across any system audio source without cloud APIs.

  • Project
    royshil/obs-localvocal

    An OBS plugin that provides real-time, local speech-to-text transcription and translation using OpenAI's Whisper, ensuring privacy and no cloud costs.

  • Project
    collabora/WhisperLive

    WhisperLive is an open‑source, near‑real‑time transcription server built around OpenAI’s Whisper model. It supports multiple inference back‑ends (faster‑whisper, NVIDIA TensorRT, Intel OpenVINO, AMD ROCm), offers word‑level timestamps, hot‑word boosting, speaker diarization and optional translation, and provides both simple command‑line clients and a Python streaming API. Docker images are provided for GPU and CPU deployments, and browser/iOS extensions let you transcribe audio directly from a web page or mobile device.

  • Project
    dseditor/QwenASRMiniTool

    A local, offline speech-to-text tool that converts audio and video into SRT subtitles using Qwen3-ASR and Whisper models with GPU and CPU acceleration.