whisper
| Version | 2026.144.1443 |
| Repo | superproject |
OpenAI Whisper local speech-to-text CLI (GPU-capable)
Installs openai-whisper via pixi into the default env, composing the
python + cuda + ffmpeg candies (ffmpeg is required for audio
decoding). Verifiable: the whisper CLI lands in the pixi default env,
runs --help, and ffmpeg is available for decoding.
Acceptance plan
Section titled “Acceptance plan”This candy’s plan: — the runnable spec charly check executes against a live deployment. check: steps are idempotent probes; run: steps change state.
| Intent | Step |
|---|---|
check |
the whisper CLI is installed in the pixi default env |
check |
the whisper CLI runs and prints its usage |
check |
ffmpeg is available on PATH for audio decoding |