GigaAM Voice Input

AiXenixAgents & Providers
Get it for macOS

Dictate in Russian with the bb microphone and get punctuated text, recognized on your own machine. On first load the plugin installs GigaAM v3, Sber's open Russian speech model, with a private Python and CPU-only PyTorch, so nothing is set up by hand. A 10-second phrase takes about 1 second on a 10-core CPU, and recordings over 20 seconds are split at pauses, so minute-long voice notes work. Audio never leaves the machine, or you can point the plugin at your own OpenAI-compatible transcription server. Needs Linux (x86-64 or arm64) or macOS on Apple silicon, about 2 GB of disk, 1.5 GB of RAM, and a one-time 1.2 GB download; recognizes Russian only.

Overview

View source

What you get

  • A GigaAM v3 service in Settings → AI services → Voice input.
  • Punctuated, normalized Russian text, about 1 s for a short phrase on a modern CPU.
  • Long voice notes: recordings over 20 seconds are split at pauses, so multi-minute dictation works.
  • A bb gigaam command to check status, read logs, restart, or reinstall.

How it works

On first load the plugin downloads everything it needs into its own data directory: the uv package manager, Python 3.12, CPU-only PyTorch, GigaAM, and the model. This is about 1.2 GB. It needs no root access, Docker, GPU, or API key. The plugin then keeps a small recognition server running on 127.0.0.1 and restarts it when needed. Your audio never leaves the machine.

You can also send recordings to your own OpenAI-compatible transcription server, for example GigaAM on a GPU machine.

Requirements

Linux (x86-64 or arm64) or macOS on Apple silicon, about 2 GB of disk, and 1.5 GB of free RAM. GigaAM v3 recognizes Russian only.

More in Agents & Providers 58

Add, choose, configure, route, or coordinate who runs a thread.

View all