Playground
Edit .spark source and preview
dry-run fixture output in the browser. Optional browser voice demo
uses the Web Speech API. Live runs use the Spark runtime on your
machine (Downloads).
Run dry-run to see simulated fixture output for ask, classify, model, and voice ops.
Live (local only):
- Download or build the Spark runtime
- Save your program as
my_program.spark -
Dry-run:
./spark-run.sh --dry-run my_program.spark -
Live:
export AI_GATEWAY_URL=https://your-gateway.example/v1then./spark-run.sh --live my_program.spark
API keys stay on your machine — never paste them into this page.
Browser voice demo — uses Web Speech API where
supported. Spark listen /
speak ops run locally with
./spark-run.sh --live.
Transcript
Assistant reply
Example voice program
listen -> user_text
ask "Reply briefly: {user_text}" -> reply
say reply -> "out.wav"
Next steps
Model builder wizard
Pick classify / ask / pipeline / model and copy a starter program.
Getting started
Install, verify, and run your first program.