@inetafrica/open-claudia 3.1.2 → 3.1.3

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## v3.1.3 — Pocket TTS voice-note provider
+
+- Adds Agent Space Pocket TTS as the preferred voice synthesizer for Telegram and streamed voice replies.
+- Requests WAV from the authenticated speech gateway and transcodes it to Ogg/Opus with ffmpeg.
+- Keeps local Whisper transcription unchanged and falls back to ElevenLabs, then macOS `say`, on synthesis failure.
+- Adds configurable `SPEECH_SERVICE_URL`, `SPEECH_API_KEY`, `POCKET_TTS_VOICE`, and `TTS_PROVIDER` settings while stripping the speech credential from provider subprocess environments.
+
 ## v3.1.2 — On-demand recall query + cold-walker fallback fix
 
 Two things fold in: a new `recall query` CLI so the working agent can ask long-term memory a question mid-task, and a latent reliability fix in the recall walker's fallback path.

package/core/config.js

@@ -141,6 +141,10 @@ const FFMPEG = config.FFMPEG || "";
 const ELEVENLABS_API_KEY = config.ELEVENLABS_API_KEY || process.env.ELEVENLABS_API_KEY || "";
 const ELEVENLABS_VOICE_ID = config.ELEVENLABS_VOICE_ID || process.env.ELEVENLABS_VOICE_ID || "EXAVITQu4vr4xnSDxMaL";
 const ELEVENLABS_MODEL = config.ELEVENLABS_MODEL || process.env.ELEVENLABS_MODEL || "eleven_v3";
+const SPEECH_SERVICE_URL = config.SPEECH_SERVICE_URL || process.env.SPEECH_SERVICE_URL || "https://speech.agents.kazee.africa";
+const SPEECH_API_KEY = config.SPEECH_API_KEY || process.env.SPEECH_API_KEY || "";
+const POCKET_TTS_VOICE = config.POCKET_TTS_VOICE || process.env.POCKET_TTS_VOICE || "alba";
+const TTS_PROVIDER = config.TTS_PROVIDER || process.env.TTS_PROVIDER || "pocket";
 const SOUL_FILE = config.SOUL_FILE || path.join(CONFIG_DIR, "soul.md");
 const CRONS_FILE = config.CRONS_FILE || path.join(CONFIG_DIR, "crons.json");
 const JOBS_FILE = config.JOBS_FILE || path.join(CONFIG_DIR, "jobs.json");
@@ -370,6 +374,7 @@ module.exports = {
   TRANSCRIPTS_DIR,
   WHISPER_CLI, WHISPER_MODEL, FFMPEG,
   ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, ELEVENLABS_MODEL,
+  SPEECH_SERVICE_URL, SPEECH_API_KEY, POCKET_TTS_VOICE, TTS_PROVIDER,
   SOUL_FILE, CRONS_FILE, JOBS_FILE, TASKS_DIR, VAULT_FILE, AUTH_FILE, IDENTITIES_FILE,
   PEOPLE_FILE, INTROS_FILE, AUDIT_FILE,
   STATE_FILE, SESSIONS_FILE,

package/core/media.js

@@ -4,7 +4,7 @@
 const fs = require("fs");
 const path = require("path");
 const { execSync } = require("child_process");
-const { WHISPER_CLI, WHISPER_MODEL, FFMPEG, TEMP_DIR, ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, ELEVENLABS_MODEL } = require("./config");
+const { WHISPER_CLI, WHISPER_MODEL, FFMPEG, TEMP_DIR, ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, ELEVENLABS_MODEL, SPEECH_SERVICE_URL, SPEECH_API_KEY, POCKET_TTS_VOICE, TTS_PROVIDER } = require("./config");
 
 const TTS_CMD = process.platform === "darwin" ? "say" : null;
 
@@ -70,10 +70,42 @@ async function elevenLabsToVoice(clean) {
   }
 }
 
+// Pocket TTS through the Agent Space speech gateway. The gateway returns WAV;
+// Telegram and voice transports receive a compact Ogg/Opus file.
+async function pocketToVoice(clean) {
+  if (TTS_PROVIDER === "elevenlabs" || !SPEECH_API_KEY || !SPEECH_SERVICE_URL || !FFMPEG) return null;
+  let wavPath = null;
+  try {
+    const res = await fetch(`${SPEECH_SERVICE_URL.replace(/\/$/, "")}/v1/audio/speech`, {
+      method: "POST",
+      headers: { Authorization: `Bearer ${SPEECH_API_KEY}`, "Content-Type": "application/json" },
+      body: JSON.stringify({ input: clean, voice: POCKET_TTS_VOICE, response_format: "wav" }),
+      signal: AbortSignal.timeout(60000),
+    });
+    if (!res.ok) {
+      console.error(`Pocket TTS failed: HTTP ${res.status}`);
+      return null;
+    }
+    const stem = `tts-pocket-${Date.now()}-${Math.random().toString(36).slice(2, 6)}`;
+    wavPath = path.join(TEMP_DIR, `${stem}.wav`);
+    const oggPath = path.join(TEMP_DIR, `${stem}.ogg`);
+    fs.writeFileSync(wavPath, Buffer.from(await res.arrayBuffer()));
+    execSync(`"${FFMPEG}" -i "${wavPath}" -c:a libopus -y "${oggPath}" 2>/dev/null`, { timeout: 30000 });
+    return oggPath;
+  } catch (e) {
+    console.error("Pocket TTS error:", e.message);
+    return null;
+  } finally {
+    if (wavPath) { try { fs.unlinkSync(wavPath); } catch (e) {} }
+  }
+}
+
 // Natural voice via ElevenLabs, falling back to macOS `say` only on no-key/error.
 async function textToVoice(text) {
   const clean = cleanForTTS(text);
   if (!clean) return null;
+  const pocket = await pocketToVoice(clean);
+  if (pocket) return pocket;
   const eleven = await elevenLabsToVoice(clean);
   if (eleven) return eleven;
   return sayToVoice(clean);
@@ -105,6 +137,8 @@ function splitSentences(text, minLen = 30) {
 async function synthSentenceMp3(text) {
   const clean = cleanForTTS(text);
   if (!clean) return null;
+  const pocket = await pocketToVoice(clean);
+  if (pocket) return pocket;
   if (!ELEVENLABS_API_KEY) return sayToVoice(clean); // ogg fallback
   try {
     const res = await fetch(`https://api.elevenlabs.io/v1/text-to-speech/${ELEVENLABS_VOICE_ID}`, {
@@ -131,4 +165,4 @@ async function synthSentenceMp3(text) {
   }
 }
 
-module.exports = { transcribeAudio, textToVoice, splitSentences, synthSentenceMp3, TTS_CMD };
+module.exports = { transcribeAudio, textToVoice, splitSentences, synthSentenceMp3, pocketToVoice, TTS_CMD };

package/core/providers/env.js

@@ -53,6 +53,7 @@ const CONTROL_PLANE_KEYS = Object.freeze([
   "OC_SEND_TOKEN",
   "VOICE_BRIDGE_TOKEN",
   "ELEVENLABS_API_KEY",
+  "SPEECH_API_KEY",
   "AGENTSPACE_POD_TOKEN",
   "WEB_PASSWORD",
   "OPEN_CLAUDIA_KEYRING_CANARY",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inetafrica/open-claudia",
-  "version": "3.1.2",
+  "version": "3.1.3",
   "description": "An always-on, provider-agnostic coding-agent harness for Claude Code and OpenAI Codex via chat",
   "main": "bot.js",
   "bin": {

package/test-provider-language.js

@@ -157,17 +157,10 @@ assert.match(pkg.description, /provider-agnostic coding-agent harness/i);
 // never re-offers a sign-in); a 🔁 Switch account button on connected
 // providers in /login behind an explicit confirm that names the signed-in
 // account where the CLI exposes it, then chains logout → fresh login.
-// 3.1.2 approved by Sumeet 2026-07-20 ("If everything you have works and is
-// ready fold it in and push all out in a new version"): on-demand recall query
-// CLI (`open-claudia recall query "<question>"`) — seeds the graph with the
-// agent's OWN working context (not the user's words), walks it with the
-// active-provider judge, returns pack sections + why-bullets; closes the
-// cold-start hole where mid-build vocabulary shared no words with the governing
-// pack. Also fixes a latent cold-walker bug: the warm→cold fallback sent an
-// array-typed outputSchema the Anthropic API rejects 400, so every fallback
-// silently failed-open — removed; freeform JSON parse is the proven contract on
-// both paths.
-assert.strictEqual(pkg.version, "3.1.2", "release version must remain unchanged without explicit approval");
+// 3.1.3 approved by Sumeet 2026-07-21 ("ok fine go ahead") for Pocket TTS
+// as the preferred voice-note provider, with ElevenLabs fallback and local
+// Whisper transcription unchanged.
+assert.strictEqual(pkg.version, "3.1.3", "release version must remain unchanged without explicit approval");
 for (const keyword of ["claude", "codex", "coding-agent", "provider-agnostic"]) {
   assert.ok(pkg.keywords.includes(keyword), `package keyword missing: ${keyword}`);
 }