Files
whisper.cpp/examples/command.wasm/README.md
Greg Sadetsky a16da91365 examples : update links in wasm examples (#3318)
* fix 404 link

* update link in whisper.wasm example

* update example in command.wasm

* update link in bench.wasm example

* update link in stream.wasm example
2025-07-12 23:22:35 +02:00

1.1 KiB

command.wasm

This is a basic Voice Assistant example that accepts voice commands from the microphone. It runs in fully in the browser via WebAseembly.

Online demo: https://ggml.ai/whisper.cpp/command.wasm/

Terminal version: examples/command

Build instructions

# build using Emscripten (v3.1.2)
git clone https://github.com/ggerganov/whisper.cpp
cd whisper.cpp
mkdir build-em && cd build-em
emcmake cmake ..
make -j libcommand

The example can then be started by running a local HTTP server:

python3 examples/server.py

And then opening a browser to the following URL: http://localhost:8000/command.wasm/

To run the example in a different server, you need to copy the following files to the server's HTTP path:

cp bin/command.wasm/*       /path/to/html/
cp bin/libcommand.js        /path/to/html/
cp bin/libcommand.worker.js /path/to/html/

📝 Note: As of Emscripten 3.1.58 (April 2024), separate worker.js files are no longer generated and the worker is embedded in the main JS file. So the worker file will not be geneated for versions later than 3.1.58.