@drakulavich/kesha-voice-kit 1.0.8 → 1.0.10

package/README.md

@@ -37,34 +37,36 @@ bun add -g @drakulavich/kesha-voice-kit
 kesha install
 ```
 
-**Then register the OpenClaw plugin:**
+**Then configure OpenClaw to use Kesha for audio transcription:**
 
 ```bash
 openclaw plugins install @drakulavich/kesha-voice-kit
+openclaw config set tools.media.audio.models \
+  '[{"type":"cli","command":"kesha","args":["--format","transcript","{{MediaPath}}"],"timeoutSeconds":15}]'
+openclaw config set tools.media.audio.enabled true
+openclaw gateway restart
 ```
 
-OpenClaw will auto-detect [`openclaw.plugin.json`](./openclaw.plugin.json) and load [`openclaw-plugin.cjs`](./openclaw-plugin.cjs), which registers `kesha-voice-kit` as a media-understanding provider with `autoPriority.audio = 50`. Once you enable audio transcription (`tools.media.audio.enabled: true`) in your OpenClaw config, Kesha becomes the default provider — higher priority than cloud providers like Groq (20).
+Your agent receives a voice message in Telegram/WhatsApp/Slack, Kesha transcribes it locally, and the agent sees enriched context:
 
-Manage the plugin 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, and the transcript flows back into the agent loop:
-
-```json
-{
-  "text": "Привет, как дела?",
-  "model": "parakeet-tdt-0.6b-v3"
-}
 ```
+Привет, как дела?
+[lang: ru, confidence: 1.00]
+```
+
+Manage the plugin with `openclaw plugins list`, `openclaw plugins disable kesha-voice-kit`, or `openclaw plugins uninstall kesha-voice-kit`.
 
 ## CLI Tools
 
 ```bash
-kesha install                    # download engine and models
-kesha audio.ogg                  # transcribe
-kesha --json audio.ogg           # JSON output with language info
-kesha --verbose audio.ogg        # show language detection details
-kesha --lang en audio.ogg        # warn if detected language differs
-kesha status                     # show installed backend info
+kesha install                              # download engine and models
+kesha audio.ogg                            # transcribe (plain text)
+kesha --format transcript audio.ogg        # text + language/confidence
+kesha --format json audio.ogg              # full JSON with lang fields
+kesha --json audio.ogg                     # alias for --format json
+kesha --verbose audio.ogg                  # show language detection details
+kesha --lang en audio.ogg                  # warn if detected language differs
+kesha status                               # show installed backend info
 ```
 
 Stdout: transcript. Stderr: errors. Pipe-friendly.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@drakulavich/kesha-voice-kit",
-  "version": "1.0.8",
+  "version": "1.0.10",
   "description": "Open-source voice toolkit for Apple Silicon. Speech-to-text, language detection. 25 languages.",
   "type": "module",
   "bin": {

package/src/cli.ts

@@ -30,6 +30,7 @@ interface MainCommandArgs {
   _: string[];
   json: boolean;
   verbose: boolean;
+  format?: string;
   lang?: string;
 }
 
@@ -113,6 +114,10 @@ export const mainCommand = defineCommand({
       description: "Show language detection details",
       default: false,
     },
+    format: {
+      type: "string",
+      description: "Output format: transcript (enriched text with lang/confidence)",
+    },
     lang: {
       type: "string",
       description: "Expected language code (ISO 639-1), warn if mismatch",
@@ -129,7 +134,7 @@ export const mainCommand = defineCommand({
     let hasError = false;
     const results: TranscribeResult[] = [];
 
-    const wantsLangId = !!(args.lang || args.verbose || args.json);
+    const wantsLangId = !!(args.lang || args.verbose || args.json || args.format === "transcript" || args.format === "json");
 
     for (const file of files) {
       try {
@@ -178,8 +183,10 @@ export const mainCommand = defineCommand({
       }
     }
 
-    if (args.json) {
+    if (args.json || args.format === "json") {
       process.stdout.write(formatJsonOutput(results));
+    } else if (args.format === "transcript") {
+      process.stdout.write(formatTranscriptOutput(results));
     } else if (args.verbose) {
       process.stdout.write(formatVerboseOutput(results));
     } else {
@@ -258,6 +265,23 @@ export function formatVerboseOutput(results: TranscribeResult[]): string {
     .join("\n") + "\n";
 }
 
+export function formatTranscriptOutput(results: TranscribeResult[]): string {
+  return results
+    .map((r, i) => {
+      const lines: string[] = [];
+      if (results.length > 1) {
+        if (i > 0) lines.push("");
+        lines.push(`=== ${r.file} ===`);
+      }
+      lines.push(r.text);
+      const lang = r.textLanguage?.code || r.audioLanguage?.code || r.lang;
+      const confidence = r.textLanguage?.confidence ?? r.audioLanguage?.confidence;
+      if (lang) lines.push(`[lang: ${lang}${confidence != null ? `, confidence: ${confidence.toFixed(2)}` : ""}]`);
+      return lines.join("\n");
+    })
+    .join("\n") + "\n";
+}
+
 export function formatJsonOutput(results: TranscribeResult[]): string {
   return JSON.stringify(results, null, 2) + "\n";
 }