feat(tts): add native VoxCPM2 backend

.github/workflows/release.yml

@@ -85,6 +85,7 @@ jobs:
           pip install -r backend/requirements.txt
           pip install --no-deps chatterbox-tts
           pip install --no-deps hume-tada
+          pip install --no-deps "voxcpm>=2.0.3,<2.1"
           pip install --no-deps omnivoice
 
       - name: Install MLX dependencies (Apple Silicon only)
@@ -294,6 +295,7 @@ jobs:
           pip install -r backend/requirements.txt
           pip install --no-deps chatterbox-tts
           pip install --no-deps hume-tada
+          pip install --no-deps "voxcpm>=2.0.3,<2.1"
           pip install --no-deps omnivoice
 
       - name: Install PyTorch with CUDA 12.8
@@ -457,6 +459,7 @@ jobs:
           pip install -r backend/requirements.txt
           pip install --no-deps chatterbox-tts
           pip install --no-deps hume-tada
+          pip install --no-deps "voxcpm>=2.0.3,<2.1"
           pip install --no-deps omnivoice
 
       - name: Build ROCm server binary (onedir)

Dockerfile

@@ -63,6 +63,7 @@ RUN if [ "$PYTORCH_VARIANT" = "rocm" ]; then \
 RUN pip install --no-cache-dir --prefix=/install -r requirements.txt
 RUN pip install --no-cache-dir --prefix=/install --no-deps chatterbox-tts
 RUN pip install --no-cache-dir --prefix=/install --no-deps hume-tada
+RUN pip install --no-cache-dir --prefix=/install --no-deps "voxcpm>=2.0.3,<2.1"
 RUN pip install --no-cache-dir --prefix=/install --no-deps omnivoice
 RUN pip install --no-cache-dir --prefix=/install \
     git+https://github.com/QwenLM/Qwen3-TTS.git

README.md

@@ -87,16 +87,16 @@ Voicebox is built and maintained with [Capy](https://capy.ai?utm_source=voicebox
 
 ## What is Voicebox?
 
-Voicebox is a **local-first AI voice studio** — a free and open-source alternative to **ElevenLabs** and **WisprFlow** in one app. Clone voices from a few seconds of audio, generate speech in 23 languages across 8 TTS engines, dictate into any text field with a global hotkey, and give any MCP-aware AI agent a voice of your choosing.
+Voicebox is a **local-first AI voice studio** — a free and open-source alternative to **ElevenLabs** and **WisprFlow** in one app. Clone voices from a few seconds of audio, generate speech in 30 languages across 10 TTS engines, dictate into any text field with a global hotkey, and give any MCP-aware AI agent a voice of your choosing.
 
 The two cloud incumbents sit on opposite halves of the voice I/O loop — ElevenLabs on output, WisprFlow on input. Voicebox does both, bridges them with a bundled local LLM for refinement and per-profile personas, and runs the whole thing on your machine.
 
 - **Complete privacy** — models, voice data, and captures never leave your machine
-- **8 TTS engines** — Qwen3-TTS, Qwen CustomVoice, Qwen VoiceDesign, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA, and Kokoro
+- **10 TTS engines** — Qwen3-TTS, Qwen CustomVoice, Qwen VoiceDesign, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA, Kokoro, OmniVoice (non-commercial), and VoxCPM2
 - **Voice cloning and preset voices** — zero-shot cloning from a reference sample, or 50+ curated preset voices via Kokoro and Qwen CustomVoice
-- **23 languages** — from English to Arabic, Japanese, Hindi, Swahili, and more
+- **30 languages** — from English to Arabic, Japanese, Hindi, Thai, Vietnamese, and more
 - **Post-processing effects** — pitch shift, reverb, delay, chorus, compression, and filters
-- **Expressive speech** — paralinguistic tags like `[laugh]`, `[sigh]`, `[gasp]` via Chatterbox Turbo; natural-language delivery control via Qwen CustomVoice; voices described in plain language via Qwen VoiceDesign
+- **Expressive speech** — paralinguistic tags like `[laugh]`, `[sigh]`, `[gasp]` via Chatterbox Turbo; natural-language delivery control via Qwen CustomVoice and VoxCPM2; voices described in plain language via Qwen VoiceDesign
 - **Unlimited length** — auto-chunking with crossfade for scripts, articles, and chapters
 - **Stories editor** — multi-track timeline for conversations, podcasts, and narratives
 - **Voice input** — global dictation hotkey with push-to-talk and toggle modes, accessibility-verified auto-paste on macOS, in-app mic on every text field, Whisper-based STT
@@ -129,7 +129,7 @@ The two cloud incumbents sit on opposite halves of the voice I/O loop — Eleven
 
 ### Multi-Engine Voice Cloning
 
-Eight TTS engines with different strengths, switchable per-generation:
+Ten TTS engines with different strengths, switchable per-generation:
 
 | Engine                      | Languages | Strengths                                                                                                                                |
 | --------------------------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
@@ -141,11 +141,13 @@ Eight TTS engines with different strengths, switchable per-generation:
 | **Chatterbox Turbo**        | English   | Fast 350M model with paralinguistic emotion/sound tags                                                                                   |
 | **TADA** (1B / 3B)          | 10        | HumeAI speech-language model — 700s+ coherent audio, text-acoustic dual alignment                                                        |
 | **Kokoro**                  | 8         | 50 curated preset voices, tiny 82M model, fast CPU inference                                                                             |
+| **VoxCPM2**                 | 30        | 2B multilingual model, 48kHz output, high-fidelity reference-audio cloning; CUDA or CPU fallback                                        |
+| **OmniVoice**               | 23 exposed | Multilingual cloning and attribute instructions; CC-BY-NC weights, non-commercial use only                                               |
 
 ### Emotions & Paralinguistic Tags
 
 Only **Chatterbox Turbo** interprets paralinguistic tags like `[laugh]` and
-`[sigh]`. Qwen3-TTS, LuxTTS, Chatterbox Multilingual, and HumeAI TADA read them
+`[sigh]`. Qwen3-TTS, LuxTTS, Chatterbox Multilingual, HumeAI TADA, and VoxCPM2 read them
 literally as text.
 
 With **Chatterbox Turbo** selected, type `/` in the text input to open the tag
@@ -393,7 +395,7 @@ Full API documentation available at `http://127.0.0.1:17493/docs`.
 | Frontend      | React, TypeScript, Tailwind CSS                                                 |
 | State         | Zustand, React Query                                                            |
 | Backend       | FastAPI (Python)                                                                |
-| TTS Engines   | Qwen3-TTS, Qwen CustomVoice, Qwen VoiceDesign, LuxTTS, Chatterbox, Chatterbox Turbo, TADA, Kokoro |
+| TTS Engines   | Qwen3-TTS, Qwen CustomVoice, Qwen VoiceDesign, LuxTTS, Chatterbox, Chatterbox Turbo, TADA, Kokoro, OmniVoice (non-commercial), VoxCPM2 |
 | STT           | Whisper / Whisper Turbo (PyTorch or MLX)                                        |
 | Local LLM     | Qwen3 (0.6B / 1.7B / 4B), shared runtime with TTS / STT                         |
 | MCP Server    | FastMCP mounted at `/mcp` (Streamable HTTP) + bundled stdio shim binary         |

app/src/components/CapturesTab/CapturesTab.tsx

@@ -269,7 +269,7 @@ export function CapturesTab() {
       // override fall through to whatever the backend picks.
       const engine = voice.default_engine as
         | 'qwen' | 'qwen_custom_voice' | 'qwen_voice_design' | 'luxtts' | 'chatterbox'
-        | 'chatterbox_turbo' | 'tada' | 'kokoro' | 'omnivoice'
+        | 'chatterbox_turbo' | 'tada' | 'kokoro' | 'omnivoice' | 'voxcpm2'
         | undefined;
       return apiClient.generateSpeech({
         profile_id: voice.id,

app/src/components/Generation/EngineModelSelector.tsx

@@ -29,6 +29,7 @@ const ENGINE_OPTIONS = [
   { value: 'tada:3B', label: 'TADA 3B Multilingual', engine: 'tada' },
   { value: 'kokoro', label: 'Kokoro 82M', engine: 'kokoro' },
   { value: 'omnivoice', label: 'OmniVoice (non-commercial)', engine: 'omnivoice' },
+  { value: 'voxcpm2', label: 'VoxCPM2', engine: 'voxcpm2' },
 ] as const;
 
 const ENGINE_DESCRIPTIONS: Record<string, string> = {
@@ -41,6 +42,7 @@ const ENGINE_DESCRIPTIONS: Record<string, string> = {
   tada: 'HumeAI, 700s+ coherent audio',
   kokoro: '82M params, CPU realtime, 8 langs',
   omnivoice: '23 languages, voice design. CC-BY-NC weights: non-commercial use only',
+  voxcpm2: '2B params, 48kHz, multilingual cloning',
 };
 
 /** Engines that only support English and should force language to 'en' on select. */
@@ -54,6 +56,7 @@ const CLONING_ENGINES = new Set([
   'chatterbox_turbo',
   'tada',
   'omnivoice',
+  'voxcpm2',
 ]);
 
 /** Engines that synthesise a voice from a written description. */

app/src/components/Generation/FloatingGenerateBox.tsx

@@ -154,7 +154,8 @@ export function FloatingGenerateBox({
     | 'kokoro'
     | 'qwen_custom_voice'
     | 'qwen_voice_design'
-    | 'omnivoice';
+    | 'omnivoice'
+    | 'voxcpm2';
   useEffect(() => {
     if (selectedProfile?.language) {
       form.setValue('language', selectedProfile.language as LanguageCode);

app/src/components/ServerSettings/ModelManagement.tsx

@@ -71,6 +71,8 @@ const MODEL_DESCRIPTIONS: Record<string, string> = {
     'Kokoro 82M by hexgrad. Tiny 82M-parameter TTS that runs at CPU realtime. Supports 8 languages with pre-built voice styles. Apache 2.0 licensed.',
   omnivoice:
     'OmniVoice by k2-fsa. Zero-shot voice cloning via a diffusion language model, plus attribute-based voice design (gender, age, pitch, accent). The model covers 600+ languages; Voicebox exposes the 23 in its own language list. 24kHz output. NON-COMMERCIAL: the weights are CC-BY-NC (code is Apache 2.0; the bundled Higgs Audio V2 codec is under the Boson community licence), so do not use output commercially.',
+  voxcpm2:
+    'VoxCPM2 by OpenBMB. A 2B-parameter multilingual TTS model with 48kHz output and high-fidelity reference-audio voice cloning.',
   'qwen-custom-voice-1.7B':
     'Qwen3-TTS CustomVoice 1.7B by Alibaba. 9 premium preset voices with instruct-based style control for tone, emotion, and prosody. Supports 10 languages.',
   'qwen-custom-voice-0.6B':
@@ -420,7 +422,8 @@ export function ModelManagement() {
         m.model_name.startsWith('chatterbox') ||
         m.model_name.startsWith('tada') ||
         m.model_name.startsWith('kokoro') ||
-        m.model_name.startsWith('omnivoice'),
+        m.model_name.startsWith('omnivoice') ||
+        m.model_name.startsWith('voxcpm2'),
     ) ?? [];
   const whisperModels = modelStatus?.models.filter((m) => m.model_name.startsWith('whisper')) ?? [];
   const llmModels = modelStatus?.models.filter((m) => m.model_name.startsWith('qwen3-')) ?? [];

app/src/components/VoiceProfiles/ProfileForm.tsx

@@ -76,6 +76,7 @@ const DEFAULT_ENGINE_OPTIONS = [
   { value: 'tada', label: 'TADA' },
   { value: 'kokoro', label: 'Kokoro 82M' },
   { value: 'omnivoice', label: 'OmniVoice (non-commercial)' },
+  { value: 'voxcpm2', label: 'VoxCPM2' },
 ] as const;
 
 function makeProfileSchema(t: (key: string) => string) {

app/src/i18n/locales/en/translation.json

@@ -890,7 +890,7 @@
           "body": "A few seconds of reference audio is enough. Multi-sample support for higher quality when you want it."
         },
         "engines": {
-          "title": "Seven engines, 23 languages.",
+          "title": "Ten engines, 30 languages.",
           "body": "Pick the tradeoff that fits — quality, speed, or multilingual coverage."
         },
         "agentReady": {

app/src/i18n/locales/es/translation.json

@@ -889,7 +889,7 @@
           "body": "Bastan unos segundos de audio de referencia. Compatible con varias muestras para mayor calidad cuando lo necesites."
         },
         "engines": {
-          "title": "Siete motores, 23 idiomas.",
+          "title": "Diez motores, 30 idiomas.",
           "body": "Elige el equilibrio que encaje: calidad, velocidad o cobertura multilingüe."
         },
         "agentReady": {

app/src/i18n/locales/fr/translation.json

@@ -889,7 +889,7 @@
           "body": "Quelques secondes d'audio de référence suffisent. Prise en charge multi-échantillons pour une qualité supérieure quand vous le souhaitez."
         },
         "engines": {
-          "title": "Sept moteurs, 23 langues.",
+          "title": "Dix moteurs, 30 langues.",
           "body": "Choisissez le compromis qui vous convient — qualité, vitesse ou couverture multilingue."
         },
         "agentReady": {

app/src/i18n/locales/it/translation.json

@@ -889,7 +889,7 @@
           "body": "Bastano pochi secondi di audio di riferimento. Supporto multi-campione per una qualità superiore quando ne hai bisogno."
         },
         "engines": {
-          "title": "Sette motori, 23 lingue.",
+          "title": "Dieci motori, 30 lingue.",
           "body": "Scegli il compromesso più adatto alle tue esigenze tra qualità, velocità o copertura multilingue."
         },
         "agentReady": {

app/src/i18n/locales/ja/translation.json

@@ -889,7 +889,7 @@
           "body": "数秒のリファレンス音声があれば十分です。より高い品質を求めるときは複数サンプルにも対応します。"
         },
         "engines": {
-          "title": "7 つのエンジン、23 言語。",
+          "title": "10 のエンジン、30 言語。",
           "body": "品質、速度、多言語対応 — 用途に合ったトレードオフを選べます。"
         },
         "agentReady": {

app/src/i18n/locales/ko/translation.json

@@ -889,7 +889,7 @@
           "body": "몇 초의 참조 오디오면 충분합니다. 원할 경우 여러 샘플로 더 높은 품질 지원."
         },
         "engines": {
-          "title": "7개 엔진, 23개 언어.",
+          "title": "10개 엔진, 30개 언어.",
           "body": "품질, 속도, 다국어 지원 중 원하는 트레이드오프를 선택하세요."
         },
         "agentReady": {

app/src/i18n/locales/pt-BR/translation.json

@@ -889,7 +889,7 @@
           "body": "Alguns segundos de áudio de referência já bastam. Suporte a múltiplas amostras para maior qualidade quando você quiser."
         },
         "engines": {
-          "title": "Sete motores, 23 idiomas.",
+          "title": "Dez motores, 30 idiomas.",
           "body": "Escolha o equilíbrio ideal — qualidade, velocidade ou cobertura multilíngue."
         },
         "agentReady": {

app/src/i18n/locales/zh-CN/translation.json

@@ -889,7 +889,7 @@
           "body": "几秒钟的参考音频就足够了。需要更高质量时,支持多样本克隆。"
         },
         "engines": {
-          "title": "七种引擎,23 种语言。",
+          "title": "十种引擎，30 种语言。",
           "body": "选择最合适的取舍——质量、速度,或多语言覆盖。"
         },
         "agentReady": {

app/src/i18n/locales/zh-TW/translation.json

@@ -889,7 +889,7 @@
           "body": "幾秒鐘的參考音訊就夠了。需要更高品質時也支援多樣本。"
         },
         "engines": {
-          "title": "七種引擎、23 種語言。",
+          "title": "十種引擎、30 種語言。",
           "body": "選擇最符合需求的取捨——品質、速度,或多語言覆蓋。"
         },
         "agentReady": {

app/src/lib/api/types.ts

@@ -80,7 +80,8 @@ export interface GenerationRequest {
     | 'chatterbox_turbo'
     | 'tada'
     | 'kokoro'
-    | 'omnivoice';
+    | 'omnivoice'
+    | 'voxcpm2';
   instruct?: string;
   /** When true and the profile has a personality prompt, input text is rewritten in-character before TTS. */
   personality?: boolean;

app/src/lib/constants/engines.ts

@@ -9,12 +9,14 @@
  * VoiceDesign take free-form prose ("speak in an angry tone"; VoiceDesign
  * layers it on top of the profile's stored design prompt), while OmniVoice
  * takes a closed vocabulary of attributes ("female, low pitch, british
- * accent") and raises on anything outside it.
+ * accent") and raises on anything outside it. VoxCPM2 maps free-form prose
+ * to a parenthesized delivery prefix in the backend.
  */
 export const INSTRUCT_ENGINES: ReadonlySet<string> = new Set([
   'qwen_custom_voice',
   'qwen_voice_design',
   'omnivoice',
+  'voxcpm2',
 ]);
 
 /** Whether the given engine should show and forward the instruct field. */

app/src/lib/constants/languages.ts

@@ -6,6 +6,7 @@
  * Chatterbox Multilingual supports 23 languages.
  * Chatterbox Turbo is English-only.
  * Kokoro supports 8 languages.
+ * VoxCPM2 supports 30 languages.
  */
 
 /** All languages that any engine supports. */
@@ -20,18 +21,25 @@ export const ALL_LANGUAGES = {
   fr: 'French',
   he: 'Hebrew',
   hi: 'Hindi',
+  id: 'Indonesian',
   it: 'Italian',
   ja: 'Japanese',
+  km: 'Khmer',
   ko: 'Korean',
+  lo: 'Lao',
   ms: 'Malay',
+  my: 'Burmese',
   nl: 'Dutch',
   no: 'Norwegian',
   pl: 'Polish',
   pt: 'Portuguese',
   ru: 'Russian',
   sv: 'Swedish',
   sw: 'Swahili',
+  th: 'Thai',
+  tl: 'Tagalog',
   tr: 'Turkish',
+  vi: 'Vietnamese',
   zh: 'Chinese',
 } as const;
 
@@ -71,8 +79,7 @@ export const ENGINE_LANGUAGES: Record<string, readonly LanguageCode[]> = {
   kokoro: ['en', 'es', 'fr', 'hi', 'it', 'pt', 'ja', 'zh'],
   qwen_custom_voice: ['zh', 'en', 'ja', 'ko', 'de', 'fr', 'ru', 'pt', 'es', 'it'],
   qwen_voice_design: ['zh', 'en', 'ja', 'ko', 'de', 'fr', 'ru', 'pt', 'es', 'it'],
-  // OmniVoice covers 600+ languages. Listed here are the ones ALL_LANGUAGES
-  // already knows -- widening that list is a separate change.
+  // Keep OmniVoice's validated 23-language subset; VoxCPM2 adds seven more below.
   omnivoice: [
     'ar',
     'da',
@@ -98,6 +105,38 @@ export const ENGINE_LANGUAGES: Record<string, readonly LanguageCode[]> = {
     'tr',
     'zh',
   ],
+  voxcpm2: [
+    'ar',
+    'da',
+    'de',
+    'el',
+    'en',
+    'es',
+    'fi',
+    'fr',
+    'he',
+    'hi',
+    'id',
+    'it',
+    'ja',
+    'km',
+    'ko',
+    'lo',
+    'ms',
+    'my',
+    'nl',
+    'no',
+    'pl',
+    'pt',
+    'ru',
+    'sv',
+    'sw',
+    'th',
+    'tl',
+    'tr',
+    'vi',
+    'zh',
+  ],
 } as const;
 
 /** Helper: get language options for a given engine. */

app/src/lib/hooks/useGenerationForm.ts

@@ -30,6 +30,7 @@ const generationSchema = z.object({
       'tada',
       'kokoro',
       'omnivoice',
+      'voxcpm2',
     ])
     .optional(),
   personality: z.boolean().optional(),
@@ -107,9 +108,11 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
                     ? 'qwen-voice-design-1.7B'
                     : engine === 'omnivoice'
                       ? 'omnivoice'
-                      : engine === 'qwen_custom_voice'
-                        ? `qwen-custom-voice-${data.modelSize}`
-                        : `qwen-tts-${data.modelSize}`;
+                      : engine === 'voxcpm2'
+                        ? 'voxcpm2'
+                        : engine === 'qwen_custom_voice'
+                          ? `qwen-custom-voice-${data.modelSize}`
+                          : `qwen-tts-${data.modelSize}`;
       const displayName =
         engine === 'luxtts'
           ? 'LuxTTS'
@@ -127,13 +130,15 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
                     ? 'Qwen VoiceDesign 1.7B'
                     : engine === 'omnivoice'
                       ? 'OmniVoice'
-                      : engine === 'qwen_custom_voice'
-                        ? data.modelSize === '1.7B'
-                          ? 'Qwen CustomVoice 1.7B'
-                          : 'Qwen CustomVoice 0.6B'
-                        : data.modelSize === '1.7B'
-                          ? 'Qwen TTS 1.7B'
-                          : 'Qwen TTS 0.6B';
+                      : engine === 'voxcpm2'
+                        ? 'VoxCPM2'
+                        : engine === 'qwen_custom_voice'
+                          ? data.modelSize === '1.7B'
+                            ? 'Qwen CustomVoice 1.7B'
+                            : 'Qwen CustomVoice 0.6B'
+                          : data.modelSize === '1.7B'
+                            ? 'Qwen TTS 1.7B'
+                            : 'Qwen TTS 0.6B';
 
       // Check if model needs downloading
       try {

app/src/lib/utils/format.ts

@@ -64,6 +64,7 @@ const ENGINE_DISPLAY_NAMES: Record<string, string> = {
   chatterbox_turbo: 'Chatterbox Turbo',
   tada: 'TADA',
   kokoro: 'Kokoro 82M',
+  voxcpm2: 'VoxCPM2',
 };
 
 export function formatEngineName(engine?: string, modelSize?: string): string {