@n1creator/openacp-cli 2026.712.12 → 2026.713.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (8) hide show
  1. package/README.md +1 -1
  2. package/dist/cli.js +3026 -1610
  3. package/dist/cli.js.map +1 -1
  4. package/dist/data/plugin-catalog.json +7 -0
  5. package/dist/index.d.ts +16 -1
  6. package/dist/index.js +1579 -517
  7. package/dist/index.js.map +1 -1
  8. package/package.json +1 -1
package/README.md CHANGED
@@ -103,7 +103,7 @@ audio attachment
103
103
  - `local-whisper` runs on the OpenACP host without an API key and reuses its environment and model cache.
104
104
  - Groq provides an optional hosted STT path.
105
105
  - Failed transcription preserves the original audio instead of silently dropping it.
106
- - Providers and local model settings are available through plugin settings and the API.
106
+ - Open **Settings → Speech-to-Text** (or use `/speech` on any command-capable connector) to choose Off, Local, or Groq and edit local model settings. Groq keys are write-only; changes hot-reload without replacing TTS providers.
107
107
 
108
108
  Local Whisper requires Python 3 and either `uv` or `python3-venv`; its runtime is prepared on first use. See [Voice and Speech](https://github.com/an1creator/OpenACP/blob/main/docs/gitbook/using-openacp/voice-and-speech.md).
109
109