@tractorscorch/clank 1.3.0 → 1.3.1

package/CHANGELOG.md

@@ -6,6 +6,15 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
 ---
 
+## [1.3.1] — 2026-03-23
+
+### Fixed
+- **STT not working** — local whisper.cpp was selected by default but not installed. Added Groq as the recommended free STT provider (whisper-large-v3-turbo).
+- **STT provider priority:** Groq (free, fast) → OpenAI Whisper → local whisper.cpp
+- **Setup wizard:** STT now offers Groq as option 1 (recommended), OpenAI as option 2, local as option 3
+
+---
+
 ## [1.3.0] — 2026-03-23
 
 ### Added

package/dist/index.js

@@ -3931,11 +3931,9 @@ var init_tts = __esm({
       constructor(config) {
         this.config = config;
       }
-      /** Check if TTS is available */
       isAvailable() {
         return !!(this.config.integrations.elevenlabs?.enabled && this.config.integrations.elevenlabs?.apiKey);
       }
-      /** Convert text to speech */
       async synthesize(text, opts) {
         const elevenlabs = this.config.integrations.elevenlabs;
         if (!elevenlabs?.enabled || !elevenlabs.apiKey) return null;
@@ -3953,29 +3951,21 @@ var init_tts = __esm({
               body: JSON.stringify({
                 text,
                 model_id: model,
-                voice_settings: {
-                  stability: 0.5,
-                  similarity_boost: 0.75
-                }
+                voice_settings: { stability: 0.5, similarity_boost: 0.75 }
               })
             }
           );
           if (!res.ok) {
-            const err = await res.text().catch(() => "");
-            console.error(`ElevenLabs TTS error ${res.status}: ${err}`);
+            console.error(`ElevenLabs TTS error ${res.status}`);
             return null;
           }
           const arrayBuffer = await res.arrayBuffer();
-          return {
-            audioBuffer: Buffer.from(arrayBuffer),
-            format: "mp3"
-          };
+          return { audioBuffer: Buffer.from(arrayBuffer), format: "mp3" };
         } catch (err) {
           console.error(`TTS error: ${err instanceof Error ? err.message : err}`);
           return null;
         }
       }
-      /** List available voices from ElevenLabs */
       async listVoices() {
         const elevenlabs = this.config.integrations.elevenlabs;
         if (!elevenlabs?.enabled || !elevenlabs.apiKey) return [];
@@ -3996,41 +3986,55 @@ var init_tts = __esm({
       constructor(config) {
         this.config = config;
       }
-      /** Check if STT is available */
       isAvailable() {
         const whisper = this.config.integrations.whisper;
         if (whisper?.enabled) {
+          if (whisper.provider === "groq" && whisper.apiKey) return true;
           if (whisper.provider === "openai" && whisper.apiKey) return true;
           if (whisper.provider === "local") return true;
         }
         if (this.config.models.providers.openai?.apiKey) return true;
+        if (this.config.integrations.groq?.apiKey) return true;
         return false;
       }
-      /** Transcribe audio to text */
       async transcribe(audioBuffer, format = "ogg") {
         const whisper = this.config.integrations.whisper;
-        const apiKey = whisper?.apiKey || this.config.models.providers.openai?.apiKey;
-        if (apiKey && whisper?.provider !== "local") {
-          return this.transcribeOpenAI(audioBuffer, format, apiKey);
+        const groqKey = whisper?.provider === "groq" && whisper?.apiKey ? whisper.apiKey : this.config.integrations.groq?.apiKey;
+        if (groqKey) {
+          const result = await this.transcribeAPI(audioBuffer, format, groqKey, "https://api.groq.com/openai/v1/audio/transcriptions", "whisper-large-v3-turbo");
+          if (result) return result;
+        }
+        const openaiKey = whisper?.provider === "openai" && whisper?.apiKey ? whisper.apiKey : this.config.models.providers.openai?.apiKey;
+        if (openaiKey) {
+          const result = await this.transcribeAPI(audioBuffer, format, openaiKey, "https://api.openai.com/v1/audio/transcriptions", "whisper-1");
+          if (result) return result;
+        }
+        if (whisper?.provider === "local") {
+          return this.transcribeLocal(audioBuffer, format);
         }
-        return this.transcribeLocal(audioBuffer, format);
+        return null;
       }
-      /** Transcribe via OpenAI Whisper API */
-      async transcribeOpenAI(audioBuffer, format, apiKey) {
+      /** Transcribe via OpenAI-compatible API (works for both OpenAI and Groq) */
+      async transcribeAPI(audioBuffer, format, apiKey, endpoint, model) {
         try {
           const blob = new Blob([new Uint8Array(audioBuffer)], { type: `audio/${format}` });
           const formData = new FormData();
           formData.append("file", blob, `audio.${format}`);
-          formData.append("model", "whisper-1");
-          const res = await fetch("https://api.openai.com/v1/audio/transcriptions", {
+          formData.append("model", model);
+          const res = await fetch(endpoint, {
             method: "POST",
             headers: { "Authorization": `Bearer ${apiKey}` },
             body: formData
           });
-          if (!res.ok) return null;
+          if (!res.ok) {
+            const errText = await res.text().catch(() => "");
+            console.error(`STT API error ${res.status}: ${errText.slice(0, 200)}`);
+            return null;
+          }
           const data = await res.json();
           return data.text ? { text: data.text, language: data.language } : null;
-        } catch {
+        } catch (err) {
+          console.error(`STT error: ${err instanceof Error ? err.message : err}`);
           return null;
         }
       }
@@ -5673,7 +5677,7 @@ var init_server = __esm({
           res.writeHead(200, { "Content-Type": "application/json" });
           res.end(JSON.stringify({
             status: "ok",
-            version: "1.3.0",
+            version: "1.3.1",
             uptime: process.uptime(),
             clients: this.clients.size,
             agents: this.engines.size
@@ -5781,7 +5785,7 @@ var init_server = __esm({
         const hello = {
           type: "hello",
           protocol: PROTOCOL_VERSION,
-          version: "1.3.0",
+          version: "1.3.1",
           agents: this.config.agents.list.map((a) => ({
             id: a.id,
             name: a.name || a.id,
@@ -6642,27 +6646,35 @@ async function runSetup(opts) {
         console.log(green4("    ElevenLabs configured (TTS available)"));
       }
     }
-    const addWhisper = await ask(rl, cyan2("  Set up speech-to-text (Whisper)? [y/N] "));
+    const addWhisper = await ask(rl, cyan2("  Set up speech-to-text (voice messages)? [y/N] "));
     if (addWhisper.toLowerCase() === "y") {
-      console.log(dim4("    1. OpenAI Whisper API (cloud, uses OpenAI key)"));
-      console.log(dim4("    2. Local whisper.cpp (requires whisper installed)"));
+      console.log(dim4("    1. Groq (recommended \u2014 free, fast)"));
+      console.log(dim4("    2. OpenAI Whisper API (paid, uses OpenAI key)"));
+      console.log(dim4("    3. Local whisper.cpp (requires manual install)"));
       const whisperChoice = await ask(rl, cyan2("    Choice [1]: "));
-      if (whisperChoice === "2") {
+      if (whisperChoice === "3") {
         config.integrations.whisper = { enabled: true, provider: "local" };
         console.log(green4("    Local whisper.cpp configured"));
         console.log(dim4("    Make sure whisper is installed and in PATH"));
-      } else {
+      } else if (whisperChoice === "2") {
         const existingKey = config.models.providers.openai?.apiKey;
         if (existingKey) {
           config.integrations.whisper = { enabled: true, provider: "openai", apiKey: existingKey };
           console.log(green4("    Whisper configured (using existing OpenAI key)"));
         } else {
-          const key = await ask(rl, cyan2("    OpenAI API key for Whisper: "));
+          const key = await ask(rl, cyan2("    OpenAI API key: "));
           if (key.trim()) {
             config.integrations.whisper = { enabled: true, provider: "openai", apiKey: key.trim() };
             console.log(green4("    Whisper configured"));
           }
         }
+      } else {
+        console.log(dim4("    Get a free API key at: https://console.groq.com/keys"));
+        const key = await ask(rl, cyan2("    Groq API key: "));
+        if (key.trim()) {
+          config.integrations.whisper = { enabled: true, provider: "groq", apiKey: key.trim() };
+          console.log(green4("    Groq Whisper configured (free, fast)"));
+        }
       }
     }
     if (isAdvanced) {
@@ -7138,7 +7150,7 @@ async function runTui(opts) {
   ws.on("open", () => {
     ws.send(JSON.stringify({
       type: "connect",
-      params: { auth: { token }, mode: "tui", version: "1.3.0" }
+      params: { auth: { token }, mode: "tui", version: "1.3.1" }
     }));
   });
   ws.on("message", (data) => {
@@ -7567,7 +7579,7 @@ import { fileURLToPath as fileURLToPath5 } from "url";
 import { dirname as dirname5, join as join18 } from "path";
 var __filename3 = fileURLToPath5(import.meta.url);
 var __dirname3 = dirname5(__filename3);
-var version = "1.3.0";
+var version = "1.3.1";
 try {
   const pkg = JSON.parse(readFileSync(join18(__dirname3, "..", "package.json"), "utf-8"));
   version = pkg.version;