altgo documentation
altgo is a desktop speech-to-text tool. Hold the trigger key (right Alt by default), speak, and release. altgo records, transcribes and optionally polishes your speech, writes the result to the system clipboard and shows it on a single line in an overlay at the bottom of the screen.
Transcription uses one of two backends. The local backend embeds sherpa-onnx and offers SenseVoice or FireRedASR2 CTC, and works offline. The online backend calls a cloud ASR service, MiMo by default, needs no model download and requires an API key. Polishing is optional and supports the OpenAI-compatible API, the Anthropic Messages API and local models.
altgo covers four combinations of Linux and Windows on x86_64 and arm64. Linux supports Ubuntu 22.04+ on x86_64 and aarch64, and Windows supports 10+ on x86_64 and arm64. macOS is not supported.
Start here
Quick Start
Install, configure and use altgo for the first time
Configuration
Complete reference for the TOML configuration file
Usage
Recording modes, polishing and output
Architecture
Module layout, state machine and platform strategy
FAQ
Troubleshooting for recording, keys, transcription and polishing
GitHub
Source code, issues and release downloads
Highlights
| Feature | Description |
|---|---|
| Hold to record | Hold right Alt to speak and release to transcribe |
| Continuous mode | Double-press for continuous recording, suited to long speech |
| Local transcription | SenseVoice or FireRedASR2 CTC, offline and with no API key |
| Online transcription | Cloud ASR such as MiMo, no model download, API key required |
| LLM polishing | Four levels, many providers, or a fully local model |
| Clipboard and overlay | Automatic clipboard write, copy again from the overlay |
| Local history | View, copy, delete and polish again, text only |
| Platform support | Linux (X11 / Wayland, x86_64 / aarch64), Windows 10+ (x86_64 / arm64) |