@drakulavich/kesha-voice-kit 1.4.3 → 1.4.4

package/README.md

@@ -14,7 +14,7 @@
 <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, ~15x faster than Whisper on Apple Silicon, ~2.5x on CPU
-- **Text-to-speech** — Kokoro (EN) + Piper (RU) + macOS system voices, SSML preview
+- **Text-to-speech** — Kokoro (EN) + Vosk-TTS (RU) + macOS system voices, SSML preview
 - **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
 
@@ -61,12 +61,12 @@ For long / silence-heavy audio, use `--vad` (auto-on past 120 s). Details: [docs
 
 ## Text-to-speech
 
-Kesha speaks back via Kokoro-82M (English) and Piper (Russian) — voice auto-picks from the text's language:
+Kesha speaks back via Kokoro-82M (English) and Vosk-TTS (Russian) — voice auto-picks from the text's language:
 
 ```bash
-kesha install --tts                      # ~490MB (Kokoro + Piper RU + ONNX G2P, opt-in)
+kesha install --tts                      # ~990MB (Kokoro + Vosk-TTS RU, opt-in)
 kesha say "Hello, world" > hello.wav
-kesha say "Привет, мир" > privet.wav     # auto-routes to ru-denis
+kesha say "Привет, мир" > privet.wav     # auto-routes (Milena on darwin, ru-vosk-m02 elsewhere)
 ```
 
 macOS system voices, SSML, voice listing, and the full voice catalogue: [docs/tts.md](docs/tts.md).
@@ -89,7 +89,7 @@ See [BENCHMARK.md](BENCHMARK.md) for the full per-file breakdown (Russian + Engl
 | SpeechBrain ECAPA-TDNN | Audio language detection | ~86MB | [HuggingFace](https://huggingface.co/speechbrain/lang-id-voxlingua107-ecapa) |
 | Apple NLLanguageRecognizer | Text language detection | built-in | macOS system framework |
 | Silero VAD v5 (opt-in) | Voice activity detection | ~2.3MB | [snakers4/silero-vad](https://github.com/snakers4/silero-vad) |
-| Kokoro-82M / Piper (opt-in) | Text-to-speech | ~490MB | [Kokoro](https://huggingface.co/hexgrad/Kokoro-82M) · [Piper](https://github.com/rhasspy/piper) |
+| Kokoro-82M / Vosk-TTS (opt-in) | Text-to-speech | ~990MB | [Kokoro](https://huggingface.co/hexgrad/Kokoro-82M) · [Vosk-TTS](https://github.com/alphacep/vosk-tts) |
 
 All models run through `kesha-engine` — a Rust binary using [FluidAudio](https://github.com/FluidInference/FluidAudio) (CoreML) on Apple Silicon and [ort](https://github.com/pykeio/ort) (ONNX Runtime) on other platforms.
 
@@ -117,7 +117,8 @@ const text = await transcribe("audio.ogg");  // transcribe
 ## Requirements
 
 - [Bun](https://bun.sh) >= 1.3
-- macOS arm64, Linux x64, or Windows x64
+- macOS arm64 or Linux x64
+- Windows x64 temporarily unsupported in v1.5.0 — Vosk-TTS native deps trigger MSVC link conflicts. Tracked in [#216](https://github.com/drakulavich/kesha-voice-kit/issues/216).
 
 ## Contributing
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@drakulavich/kesha-voice-kit",
-  "version": "1.4.3",
-  "description": "Open-source voice toolkit. Speech-to-text (25 langs, ~19x faster than Whisper on Apple Silicon, ONNX fallback on CPU), text-to-speech (Kokoro + Piper + ~180 macOS system voices, SSML), voice-activity detection, language detection (107 langs). Rust engine, OpenClaw skill.",
+  "version": "1.4.4",
+  "description": "Open-source voice toolkit. Speech-to-text (25 langs, ~19x faster than Whisper on Apple Silicon, ONNX fallback on CPU), text-to-speech (Kokoro + Vosk-TTS + ~180 macOS system voices, SSML), voice-activity detection, language detection (107 langs). Rust engine, OpenClaw skill.",
   "type": "module",
   "bin": {
     "kesha": "bin/kesha.js",

package/src/cli/install.ts

@@ -92,7 +92,7 @@ export const installCommand = defineCommand({
     },
     tts: {
       type: "boolean",
-      description: "Also install TTS models (Kokoro EN + Piper RU + ONNX G2P, ~490MB)",
+      description: "Also install TTS models (Kokoro EN + Vosk-TTS RU, ~990MB)",
       default: false,
     },
     vad: {

package/src/cli/say.ts

@@ -3,17 +3,25 @@ import { detectTextLanguageEngine, getEngineBinPath } from "../engine";
 import { log } from "../log";
 import { say, SayError } from "../say";
 
+/**
+ * Darwin defaults to AVSpeech Milena — zero install, no model download required.
+ * Linux/Windows fall through to Vosk-TTS `ru-vosk-m02` (male, per CLAUDE.md
+ * "DEFAULT TTS VOICES MUST BE MALE"; replaces Piper-ruslan as of #213).
+ */
+const RU_DARWIN_FALLBACK_VOICE = "macos-com.apple.voice.compact.ru-RU.Milena";
+
 /** Map a detected language code to a default voice id. Unknown / low-confidence → undefined. */
 export function pickVoiceForLang(
   code: string | undefined,
   confidence: number,
+  platform: NodeJS.Platform = process.platform,
 ): string | undefined {
   if (!code || confidence < 0.5) return undefined;
   switch (code) {
     case "en":
-      return "en-af_heart";
+      return "en-am_michael";
     case "ru":
-      return "ru-denis";
+      return platform === "darwin" ? RU_DARWIN_FALLBACK_VOICE : "ru-vosk-m02";
     default:
       return undefined;
   }
@@ -50,7 +58,7 @@ export const sayCommand = defineCommand({
   },
   args: {
     text: { type: "positional", required: false, description: "Text to speak (stdin if omitted)" },
-    voice: { type: "string", description: "Voice id, e.g. en-af_heart" },
+    voice: { type: "string", description: "Voice id, e.g. en-am_michael" },
     lang: { type: "string", description: "BCP 47 language code (default en-us)" },
     out: { type: "string", description: "Write WAV to file instead of stdout" },
     rate: { type: "string", description: "Speaking rate 0.5–2.0", default: "1.0" },

package/src/engine-install.ts

@@ -36,7 +36,14 @@ function getEngineBinaryName(): string {
 
   if (platform === "darwin" && arch === "arm64") return "kesha-engine-darwin-arm64";
   if (platform === "linux" && arch === "x64") return "kesha-engine-linux-x64";
-  if (platform === "win32" && arch === "x64") return "kesha-engine-windows-x64.exe";
+  if (platform === "win32" && arch === "x64") {
+    throw new Error(
+      "Windows x64 is temporarily unsupported in v1.5.0 — the Vosk-TTS engine has " +
+        "native deps that trip MSVC at link time. Tracked at " +
+        "https://github.com/drakulavich/kesha-voice-kit/issues/216. " +
+        "Use v1.4.x as a workaround until the fix lands.",
+    );
+  }
 
   throw new Error(`Unsupported platform: ${platform} ${arch}`);
 }
@@ -51,7 +58,7 @@ function getEngineBinaryName(): string {
  * Best-effort: 404s (older engine versions predate the sidecar) and
  * network errors log a warning and return — macos-* voices simply won't
  * be available, which is a graceful degradation. The user keeps Kokoro +
- * Piper.
+ * Vosk-TTS.
  */
 async function downloadAVSpeechSidecar(binPath: string, engineVersion: string): Promise<void> {
   if (process.platform !== "darwin" || process.arch !== "arm64") return;
@@ -95,7 +102,7 @@ async function downloadAVSpeechSidecar(binPath: string, engineVersion: string):
 }
 
 export interface InstallOptions {
-  /** Also install Kokoro + Piper + ONNX G2P TTS models. */
+  /** Also install Kokoro + Vosk-TTS models. */
   tts?: boolean;
   /** Also install Silero VAD model for long-audio preprocessing. */
   vad?: boolean;

package/src/say.ts

@@ -8,7 +8,7 @@ export interface SayOptions {
    * arg) handles stdin separately before invoking `say()`.
    */
   text?: string;
-  /** Voice id, e.g. `en-af_heart`. Defaults to engine default. */
+  /** Voice id, e.g. `en-am_michael`. Defaults to engine default. */
   voice?: string;
   /** Override the voice's default BCP 47 language code (e.g. `en-us`, `ru`). */
   lang?: string;

package/src/status.ts

@@ -104,8 +104,7 @@ function showDiskUsage(binPath: string): void {
     { label: "Language ID", path: join(cache, "models/lang-id-ecapa") },
     { label: "VAD (Silero)", path: join(cache, "models/silero-vad") },
     { label: "TTS (Kokoro)", path: join(cache, "models/kokoro-82m") },
-    { label: "TTS (Piper)", path: join(cache, "models/piper-ru") },
-    { label: "TTS (G2P)", path: join(cache, "models/g2p") },
+    { label: "TTS (Vosk)", path: join(cache, "models/vosk-ru") },
   ];
 
   const rows: Array<{ label: string; size: number }> = [];
@@ -173,16 +172,16 @@ function listInstalledVoices(): string[] {
     /* Kokoro not installed */
   }
   try {
-    // Piper RU files follow `ru_RU-<name>-<quality>.onnx` — report just `<name>`.
-    const piper = readdirSync(join(cache, "models", "piper-ru"));
-    for (const f of piper) {
-      if (!f.endsWith(".onnx")) continue;
-      const stem = f.replace(/\.onnx$/, "");
-      const name = stem.replace(/^ru_RU-/, "").split("-")[0];
-      if (name) voices.push(`ru-${name}`);
+    // Vosk-TTS Russian is a single multi-speaker model. Mirror the Rust-side
+    // gate (models::is_vosk_ru_cached) — checking model.onnx + bert/model.onnx
+    // avoids advertising voices that would fail to load on a partial install.
+    statSync(join(cache, "models", "vosk-ru", "model.onnx"));
+    statSync(join(cache, "models", "vosk-ru", "bert", "model.onnx"));
+    for (const id of ["f01", "f02", "f03", "m01", "m02"]) {
+      voices.push(`ru-vosk-${id}`);
     }
   } catch {
-    /* Piper not installed */
+    /* Vosk not installed */
   }
   return voices.sort();
 }