@drakulavich/kesha-voice-kit 1.0.0 → 1.0.3

package/README.md

@@ -11,9 +11,9 @@
   <a href="https://bun.sh"><img src="https://img.shields.io/badge/runtime-Bun-f9f1e1?logo=bun" alt="Bun"></a>
 </p>
 
-<p align="center"><b>Open-source voice toolkit for Apple Silicon.</b><br>A collection of small, fast, open-source audio models — packaged as CLI tools and an <a href="https://github.com/openclaw/openclaw">OpenClaw</a> skill for LLM agents.</p>
+<p align="center"><b>Open-source voice toolkit.</b> Optimized for Apple Silicon (CoreML), works on any platform (ONNX fallback).<br>A collection of small, fast, open-source audio models — packaged as CLI tools and an <a href="https://github.com/openclaw/openclaw">OpenClaw</a> skill for LLM agents.</p>
 
-- **Speech-to-text** — 25 languages, ~19x faster than Whisper on Apple Silicon
+- **Speech-to-text** — 25 languages, ~19x faster than Whisper on Apple Silicon, ~2.5x on CPU
 - **Language detection** — 107 languages from audio, text language via NLLanguageRecognizer
 - **Rust engine** — single 20MB binary, no ffmpeg, no Python, no native Node addons
 - **OpenClaw-ready** — plug into your LLM agent as a voice processing skill
@@ -28,18 +28,16 @@ kesha audio.ogg     # transcript to stdout
 
 ## OpenClaw Integration
 
-Kesha Voice Kit is built as a skill for [OpenClaw](https://github.com/openclaw/openclaw) — give your LLM agent ears. No API keys, everything runs locally on your machine.
+Kesha Voice Kit ships as a plugin for [OpenClaw](https://github.com/openclaw/openclaw) — give your LLM agent ears. No API keys, everything runs locally on your machine.
 
-Add to your OpenClaw config:
+**Install the plugin** (requires the `kesha` CLI — see [Quick Start](#quick-start)):
 
-```json
-{
-  "type": "cli",
-  "command": "kesha",
-  "args": ["--json", "{{MediaPath}}"]
-}
+```bash
+openclaw plugins install @drakulavich/kesha-voice-kit
 ```
 
+OpenClaw fetches the package from npm, auto-detects [`openclaw.plugin.json`](./openclaw.plugin.json), and wires `kesha --json {{MediaPath}}` as the audio transcription backend under `tools.media.audio`. Manage it afterwards with `openclaw plugins list`, `openclaw plugins disable kesha-voice-kit`, or `openclaw plugins uninstall kesha-voice-kit`.
+
 Your agent receives a voice message in Telegram/WhatsApp/Slack. Kesha transcribes it locally, detects the language, and returns structured JSON:
 
 ```json

package/openclaw-plugin.js

@@ -0,0 +1,14 @@
+// OpenClaw plugin entry stub for Kesha Voice Kit.
+//
+// The actual wiring lives in openclaw.plugin.json's configPatch, which
+// installs `kesha --json {{MediaPath}}` under tools.media.audio. This
+// file exists only to satisfy OpenClaw's requirement that native
+// plugins declare at least one JavaScript extension in
+// package.json#openclaw.extensions — Kesha has no hooks, tools, or
+// services to register beyond the config patch itself.
+export default {
+  id: "kesha-voice-kit",
+  register() {
+    // intentionally empty — see openclaw.plugin.json
+  },
+};

package/openclaw.plugin.json

@@ -2,6 +2,7 @@
   "name": "kesha-voice-kit",
   "displayName": "Kesha Voice Kit",
   "description": "Local speech-to-text for voice messages. 25 languages, ~19x faster than Whisper on Apple Silicon. Drop-in replacement for openai-whisper.",
+  "configSchema": {},
   "configPatch": {
     "tools": {
       "media": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@drakulavich/kesha-voice-kit",
-  "version": "1.0.0",
+  "version": "1.0.3",
   "description": "Open-source voice toolkit for Apple Silicon. Speech-to-text, language detection. 25 languages.",
   "type": "module",
   "bin": {
@@ -17,11 +17,20 @@
     "package.json",
     "tsconfig.json",
     "openclaw.plugin.json",
+    "openclaw-plugin.js",
     "SKILL.md",
     "scripts/postinstall.cjs",
     "LICENSE",
     "README.md"
   ],
+  "openclaw": {
+    "extensions": [
+      "./openclaw-plugin.js"
+    ]
+  },
+  "keshaEngine": {
+    "version": "1.0.2"
+  },
   "scripts": {
     "test": "bun test",
     "test:unit": "bun test tests/unit/",

package/src/engine-install.ts

@@ -1,6 +1,6 @@
 import { dirname } from "path";
 import { existsSync, mkdirSync, chmodSync } from "fs";
-import { getEngineBinPath } from "./engine";
+import { getEngineBinPath, getEngineCapabilities } from "./engine";
 import { log } from "./log";
 import { streamResponseToFile } from "./progress";
 
@@ -25,8 +25,16 @@ export async function downloadEngine(noCache = false, backend?: string): Promise
   } else {
     const binaryName = getEngineBinaryName();
     const pkg = await Bun.file(new URL("../package.json", import.meta.url)).json();
-    const version = typeof pkg.version === "string" ? pkg.version : "unknown";
-    const url = `https://github.com/${GITHUB_REPO}/releases/download/v${version}/${binaryName}`;
+    // The engine version is tracked separately from the CLI version so
+    // CLI-only patch releases don't require cutting a new GitHub release
+    // + Rust rebuild. Fall back to the CLI version for backwards compat.
+    const engineVersion =
+      typeof pkg.keshaEngine?.version === "string"
+        ? pkg.keshaEngine.version
+        : typeof pkg.version === "string"
+        ? pkg.version
+        : "unknown";
+    const url = `https://github.com/${GITHUB_REPO}/releases/download/v${engineVersion}/${binaryName}`;
 
     mkdirSync(dirname(binPath), { recursive: true });
 
@@ -50,8 +58,17 @@ export async function downloadEngine(noCache = false, backend?: string): Promise
     log.success("Engine binary downloaded.");
   }
 
+  if (backend) {
+    const caps = await getEngineCapabilities();
+    if (caps && caps.backend !== backend) {
+      throw new Error(
+        `Requested backend "${backend}" is not available: the installed engine for this platform uses "${caps.backend}".\n  Fix: omit --${backend} to use the auto-detected backend, or run on a platform that ships the "${backend}" build.`,
+      );
+    }
+  }
+
   log.progress("Installing models...");
-  const installArgs = ["install", ...(noCache ? ["--no-cache"] : []), ...(backend ? [`--backend=${backend}`] : [])];
+  const installArgs = ["install", ...(noCache ? ["--no-cache"] : [])];
   const proc = Bun.spawnSync([binPath, ...installArgs], {
     stdout: "pipe",
     stderr: "pipe",