wavo
Local GPU speech-to-text CLI and Rust library for Parakeet, GigaAM and Whisper models.
Tested on Linux
Use it
Linux x86_64
Download dev binary and install to ~/.local/bin
mkdir -p ~/.local/bin && curl -fL -o /tmp/wavo-dev.tar.gz https://github.com/vladkens/wavo/releases/download/dev/wavo-dev-x86_64-unknown-linux-gnu.tar.gz && tar -xzf /tmp/wavo-dev.tar.gz -C /tmp && cp /tmp/wavo ~/.local/bin/wavo && chmod +x ~/.local/bin/wavo
Where the README and reality differ
- README: download the binary from the latest release
What worked: use dev-release binary (v0.3.1-23-ga3b5c3b) which has list/debug/serve and parakeet-ultra; latest release v0.3.1 binary has no wavo debug or wavo serve
Check that it works
wavo --versionThe output should contain “wavo 0.3.1-23-ga3b5c3b”.
First thing to try
wavo listRun wavo list first to see the available speech models.
What it does
- Transcribe speech to text on your own computerNot tested
- Save transcripts as SRT subtitle filesNot tested
- Run a local transcription API serverNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 0 of 3 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- transcribe an audio file to text
- generate SRT subtitles from audio
- serve OpenAI-compatible local transcription API
An alternative to transcribe.cpp, whisper.cpp and sherpa-onnx.
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 31 Oct 2026
- Version 0.3.1-23-ga3b5c3b
Differences the test machine hit
- README: cargo install wavo
In the test: download dev-release tarball wavo-dev-x86_64-unknown-linux-gnu.tar.gz and copy wavo to ~/.local/bin (cargo needs a Rust toolchain the box must not install)