diff --git a/README.md b/README.md
index 451d394..8bf3434 100644
--- a/README.md
+++ b/README.md
@@ -1,38 +1,20 @@
-
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
+## VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
+
+**English** | [δΈζ](./README_zh.md)
+
+
+
-
- English | δΈζ
-
-
-
-
-
-
-
-
-
+
-
-

-
-

-
-
+
-
- π Join our community for discussion and support!
-
-
-
Feishu
-
- |
-
-
Discord
-
-
+
+π Join our community for discussion and support!
+ [Feishu](./assets/feishu-group.png) Β |Β [Discord](https://discord.gg/KZUx7tVNwz)
VoxCPM is a **tokenizer-free** Text-to-Speech system that directly generates continuous speech representations via an end-to-end **diffusion autoregressive architecture**, bypassing discrete tokenization to achieve highly natural and expressive synthesis.
@@ -49,20 +31,17 @@ VoxCPM is a **tokenizer-free** Text-to-Speech system that directly generates con
- β‘ **Real-Time Streaming** β RTF as low as ~0.3 on NVIDIA RTX 4090, and ~0.13 accelerated by [Nano-vLLM](https://github.com/a710128/nanovllm-voxcpm) or [vLLM-Omni](https://github.com/vllm-project/vllm-omni) β official vLLM omni-modal serving for VoxCPM2 with PagedAttention and an OpenAI-compatible API
- π **Fully Open-Source & Commercial-Ready** β Weights and code released under the [Apache-2.0](LICENSE) license, free for commercial use
-
-π Supported Languages (30)
-
+**π Supported Languages (30)**
Arabic, Burmese, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Tagalog, Thai, Turkish, Vietnamese
Chinese Dialect: εε·θ―, η²€θ―, ε΄θ―, δΈεθ―, ζ²³εθ―, ιθ₯Ώθ―, ε±±δΈθ―, 倩ζ΄₯θ―, ι½εθ―
-
### News
-* **[2026.04]** π₯ We release **VoxCPM2** β 2B, 30 languages, Voice Design & Controllable Voice Cloning, 48kHz audio output! [Weights](https://huggingface.co/openbmb/VoxCPM2) | [Docs](https://voxcpm.readthedocs.io/en/latest/) | [Playground](https://huggingface.co/spaces/OpenBMB/VoxCPM-Demo) | [Technical Report](https://arxiv.org/abs/2606.06928)
-* **[2025.12]** π Open-source **VoxCPM1.5** [weights](https://huggingface.co/openbmb/VoxCPM1.5) with SFT & LoRA fine-tuning. (**π #1 GitHub Trending**)
-* **[2025.09]** π₯ Release VoxCPM [Technical Report](https://arxiv.org/abs/2509.24650).
-* **[2025.09]** π Open-source **VoxCPM-0.5B** [weights](https://huggingface.co/openbmb/VoxCPM-0.5B) (**π #1 HuggingFace Trending**)
+- **[2026.04]** π₯ We release **VoxCPM2** β 2B, 30 languages, Voice Design & Controllable Voice Cloning, 48kHz audio output! [Weights](https://huggingface.co/openbmb/VoxCPM2) | [Docs](https://voxcpm.readthedocs.io/en/latest/) | [Playground](https://huggingface.co/spaces/OpenBMB/VoxCPM-Demo) | [Technical Report](https://arxiv.org/abs/2606.06928)
+- **[2025.12]** π Open-source **VoxCPM1.5** [weights](https://huggingface.co/openbmb/VoxCPM1.5) with SFT & LoRA fine-tuning. (**π #1 GitHub Trending**)
+- **[2025.09]** π₯ Release VoxCPM [Technical Report](https://arxiv.org/abs/2509.24650).
+- **[2025.09]** π Open-source **VoxCPM-0.5B** [weights](https://huggingface.co/openbmb/VoxCPM-0.5B) (**π #1 HuggingFace Trending**)
---
@@ -185,8 +164,7 @@ wav = model.generate(
sf.write("hifi_clone.wav", wav, model.tts_model.sample_rate)
```
-
-π Streaming API
+**π Streaming API**
```python
import numpy as np
@@ -199,7 +177,8 @@ for chunk in model.generate_streaming(
wav = np.concatenate(chunks)
sf.write("streaming.wav", wav, model.tts_model.sample_rate)
```
-
+
+
### CLI Usage
@@ -252,7 +231,7 @@ Supported values are `auto`, `cpu`, `mps`, `cuda`, and `cuda:N`. On Apple Silico
### π’ Production Deployment (Nano-vLLM)
-For high-throughput serving, use [**Nano-vLLM-VoxCPM**](https://github.com/a710128/nanovllm-voxcpm) β a dedicated inference engine built on Nano-vLLM with concurrent request support and an async API.
+For high-throughput serving, use **[Nano-vLLM-VoxCPM](https://github.com/a710128/nanovllm-voxcpm)** β a dedicated inference engine built on Nano-vLLM with concurrent request support and an async API.
```bash
pip install nano-vllm-voxcpm
@@ -272,7 +251,7 @@ server.stop()
### π Production Serving (vLLM-Omni)
-For production multi-tenant deployments, use [**vLLM-Omni**](https://github.com/vllm-project/vllm-omni) β the official vLLM project's omni-modal extension with native **VoxCPM2** support. PagedAttention KV cache, continuous batching, and a drop-in **OpenAI-compatible** `/v1/audio/speech` endpoint.
+For production multi-tenant deployments, use **[vLLM-Omni](https://github.com/vllm-project/vllm-omni)** β the official vLLM project's omni-modal extension with native **VoxCPM2** support. PagedAttention KV cache, continuous batching, and a drop-in **OpenAI-compatible** `/v1/audio/speech` endpoint.
```bash
# Install from source (latest main β vllm-omni is rapidly evolving)
@@ -302,23 +281,25 @@ curl http://localhost:8000/v1/audio/speech \
## π¦ Models & Versions
-| | **VoxCPM2** | **VoxCPM1.5** | **VoxCPM-0.5B** |
-|---|:---:|:---:|:---:|
-| **Status** | π’ Latest | Stable | Legacy |
-| **Backbone Parameters** | 2B | 0.6B | 0.5B |
-| **Audio Sample Rate** | 48kHz | 44.1kHz | 16kHz |
-| **LM Token Rate** | 6.25Hz | 6.25Hz | 12.5Hz |
-| **Languages** | 30 | 2 (zh, en) | 2 (zh, en) |
-| **Cloning Mode** | Isolated Reference & Continuation | Continuation only | Continuation only |
-| **Voice Design** | β
| β | β |
-| **Controllable Voice Cloning** | β
| β | β |
-| **SFT / LoRA** | β
| β
| β
|
-| **RTF (RTX 4090)** | ~0.30 | ~0.15 | ~0.17 |
-| **RTF in Nano-VLLM (RTX 4090)** | ~0.13 | ~0.08 | ~0.10 |
-| **VRAM** | ~8 GB | ~6 GB | ~5 GB |
-| **Weights** | [π€ HF](https://huggingface.co/openbmb/VoxCPM2) / [MS](https://modelscope.cn/models/OpenBMB/VoxCPM2) | [π€ HF](https://huggingface.co/openbmb/VoxCPM1.5) / [MS](https://modelscope.cn/models/OpenBMB/VoxCPM1.5) | [π€ HF](https://huggingface.co/openbmb/VoxCPM-0.5B) / [MS](https://modelscope.cn/models/OpenBMB/VoxCPM-0.5B) |
-| **Technical Report** | [arXiv](https://arxiv.org/abs/2606.06928) | β | [arXiv](https://arxiv.org/abs/2509.24650) [ICLR 2026](https://openreview.net/forum?id=h5KLpGoqzC) |
-| **Demo Page** | [Audio Samples](https://openbmb.github.io/voxcpm2-demopage) | β | [Audio Samples](https://openbmb.github.io/VoxCPM-demopage) |
+
+| | **VoxCPM2** | **VoxCPM1.5** | **VoxCPM-0.5B** |
+| ------------------------------- | ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
+| **Status** | π’ Latest | Stable | Legacy |
+| **Backbone Parameters** | 2B | 0.6B | 0.5B |
+| **Audio Sample Rate** | 48kHz | 44.1kHz | 16kHz |
+| **LM Token Rate** | 6.25Hz | 6.25Hz | 12.5Hz |
+| **Languages** | 30 | 2 (zh, en) | 2 (zh, en) |
+| **Cloning Mode** | Isolated Reference & Continuation | Continuation only | Continuation only |
+| **Voice Design** | β
| β | β |
+| **Controllable Voice Cloning** | β
| β | β |
+| **SFT / LoRA** | β
| β
| β
|
+| **RTF (RTX 4090)** | ~0.30 | ~0.15 | ~0.17 |
+| **RTF in Nano-VLLM (RTX 4090)** | ~0.13 | ~0.08 | ~0.10 |
+| **VRAM** | ~8 GB | ~6 GB | ~5 GB |
+| **Weights** | [π€ HF](https://huggingface.co/openbmb/VoxCPM2) / [MS](https://modelscope.cn/models/OpenBMB/VoxCPM2) | [π€ HF](https://huggingface.co/openbmb/VoxCPM1.5) / [MS](https://modelscope.cn/models/OpenBMB/VoxCPM1.5) | [π€ HF](https://huggingface.co/openbmb/VoxCPM-0.5B) / [MS](https://modelscope.cn/models/OpenBMB/VoxCPM-0.5B) |
+| **Technical Report** | [arXiv](https://arxiv.org/abs/2606.06928) | β | [arXiv](https://arxiv.org/abs/2509.24650) [ICLR 2026](https://openreview.net/forum?id=h5KLpGoqzC) |
+| **Demo Page** | [Audio Samples](https://openbmb.github.io/voxcpm2-demopage) | β | [Audio Samples](https://openbmb.github.io/VoxCPM-demopage) |
+
VoxCPM2 is built on a **tokenizer-free, diffusion autoregressive** paradigm. The model operates entirely in the latent space of **AudioVAE V2**, following a four-stage pipeline: **LocEnc β TSLM β RALM β LocDiT**, enabling rich expressiveness and 48kHz native audio output.
@@ -336,186 +317,187 @@ VoxCPM2 achieves state-of-the-art or comparable results on public zero-shot and
### Seed-TTS-eval
-
-Seed-TTS-eval WER(β¬)&SIM(β¬) Results (click to expand)
-
-| Model | Parameters | Open-Source | test-EN | | test-ZH | | test-Hard | |
-|------|------|------|:------------:|:--:|:------------:|:--:|:-------------:|:--:|
-| | | | WER/%β¬ | SIM/%β¬| CER/%β¬| SIM/%β¬ | CER/%β¬ | SIM/%β¬ |
-| MegaTTS3 | 0.5B | β | 2.79 | 77.1 | 1.52 | 79.0 | - | - |
-| DiTAR | 0.6B | β | 1.69 | 73.5 | 1.02 | 75.3 | - | - |
-| CosyVoice3 | 0.5B | β | 2.02 | 71.8 | 1.16 | 78.0 | 6.08 | 75.8 |
-| CosyVoice3 | 1.5B | β | 2.22 | 72.0 | 1.12 | 78.1 | 5.83 | 75.8 |
-| Seed-TTS | - | β | 2.25 | 76.2 | 1.12 | 79.6 | 7.59 | 77.6 |
-| MiniMax-Speech | - | β | 1.65 | 69.2 | 0.83 | 78.3 | - | - |
-| F5-TTS | 0.3B | β
| 2.00 | 67.0 | 1.53 | 76.0 | 8.67 | 71.3 |
-| MaskGCT | 1B | β
| 2.62 | 71.7 | 2.27 | 77.4 | - | - |
-| CosyVoice | 0.3B | β
| 4.29 | 60.9 | 3.63 | 72.3 | 11.75 | 70.9 |
-| CosyVoice2 | 0.5B | β
| 3.09 | 65.9 | 1.38 | 75.7 | 6.83 | 72.4 |
-| SparkTTS | 0.5B | β
| 3.14 | 57.3 | 1.54 | 66.0 | - | - |
-| FireRedTTS | 0.5B | β
| 3.82 | 46.0 | 1.51 | 63.5 | 17.45 | 62.1 |
-| FireRedTTS-2 | 1.5B | β
| 1.95 | 66.5 | 1.14 | 73.6 | - | - |
-| Qwen2.5-Omni | 7B | β
| 2.72 | 63.2 | 1.70 | 75.2 | 7.97 | 74.7 |
-| Qwen3-Omni | 30B-A3B | β
| 1.39 | - | 1.07 | - | - | - |
-| OpenAudio-s1-mini | 0.5B | β
| 1.94 | 55.0 | 1.18 | 68.5 | 23.37 | 64.3 |
-| IndexTTS2 | 1.5B | β
| 2.23 | 70.6 | 1.03 | 76.5 | 7.12 | 75.5 |
-| VibeVoice | 1.5B | β
| 3.04 | 68.9 | 1.16 | 74.4 | - | - |
-| HiggsAudio-v2 | 3B | β
| 2.44 | 67.7 | 1.50 | 74.0 | 55.07 | 65.6 |
-| VoxCPM-0.5B | 0.6B | β
| 1.85 | 72.9 | 0.93 | 77.2 | 8.87 | 73.0 |
-| VoxCPM1.5 | 0.8B | β
| 2.12 | 71.4 | 1.18 | 77.0 | 7.74 | 73.1 |
-| MOSS-TTS | | β
| 1.85 | 73.4 | 1.20 | 78.8 | - | - |
-| Qwen3-TTS | 1.7B | β
| 1.23 | 71.7 | 1.22 | 77.0 | 6.76 | 74.8 |
-| FishAudio S2 | 4B | β
| 0.99 | - | 0.54 | - | 5.99 | - |
-| LongCat-Audio-DiT | 3.5B | β
| 1.50 | 78.6 | 1.09 | 81.8 | 6.04 | 79.7 |
-| **VoxCPM2** | 2B | β
| 1.84 | 75.3 | 0.97| 79.5| 8.13 | 75.3 |
-
+**Seed-TTS-eval WER(β¬)&SIM(β¬) Results (click to expand)**
+
+
+| Model | Parameters | Open-Source | test-EN | | test-ZH | | test-Hard | |
+| ----------------- | ---------- | ----------- | ------- | ------ | ------- | ------ | --------- | ------ |
+| | | | WER/%β¬ | SIM/%β¬ | CER/%β¬ | SIM/%β¬ | CER/%β¬ | SIM/%β¬ |
+| MegaTTS3 | 0.5B | β | 2.79 | 77.1 | 1.52 | 79.0 | - | - |
+| DiTAR | 0.6B | β | 1.69 | 73.5 | 1.02 | 75.3 | - | - |
+| CosyVoice3 | 0.5B | β | 2.02 | 71.8 | 1.16 | 78.0 | 6.08 | 75.8 |
+| CosyVoice3 | 1.5B | β | 2.22 | 72.0 | 1.12 | 78.1 | 5.83 | 75.8 |
+| Seed-TTS | - | β | 2.25 | 76.2 | 1.12 | 79.6 | 7.59 | 77.6 |
+| MiniMax-Speech | - | β | 1.65 | 69.2 | 0.83 | 78.3 | - | - |
+| F5-TTS | 0.3B | β
| 2.00 | 67.0 | 1.53 | 76.0 | 8.67 | 71.3 |
+| MaskGCT | 1B | β
| 2.62 | 71.7 | 2.27 | 77.4 | - | - |
+| CosyVoice | 0.3B | β
| 4.29 | 60.9 | 3.63 | 72.3 | 11.75 | 70.9 |
+| CosyVoice2 | 0.5B | β
| 3.09 | 65.9 | 1.38 | 75.7 | 6.83 | 72.4 |
+| SparkTTS | 0.5B | β
| 3.14 | 57.3 | 1.54 | 66.0 | - | - |
+| FireRedTTS | 0.5B | β
| 3.82 | 46.0 | 1.51 | 63.5 | 17.45 | 62.1 |
+| FireRedTTS-2 | 1.5B | β
| 1.95 | 66.5 | 1.14 | 73.6 | - | - |
+| Qwen2.5-Omni | 7B | β
| 2.72 | 63.2 | 1.70 | 75.2 | 7.97 | 74.7 |
+| Qwen3-Omni | 30B-A3B | β
| 1.39 | - | 1.07 | - | - | - |
+| OpenAudio-s1-mini | 0.5B | β
| 1.94 | 55.0 | 1.18 | 68.5 | 23.37 | 64.3 |
+| IndexTTS2 | 1.5B | β
| 2.23 | 70.6 | 1.03 | 76.5 | 7.12 | 75.5 |
+| VibeVoice | 1.5B | β
| 3.04 | 68.9 | 1.16 | 74.4 | - | - |
+| HiggsAudio-v2 | 3B | β
| 2.44 | 67.7 | 1.50 | 74.0 | 55.07 | 65.6 |
+| VoxCPM-0.5B | 0.6B | β
| 1.85 | 72.9 | 0.93 | 77.2 | 8.87 | 73.0 |
+| VoxCPM1.5 | 0.8B | β
| 2.12 | 71.4 | 1.18 | 77.0 | 7.74 | 73.1 |
+| MOSS-TTS | | β
| 1.85 | 73.4 | 1.20 | 78.8 | - | - |
+| Qwen3-TTS | 1.7B | β
| 1.23 | 71.7 | 1.22 | 77.0 | 6.76 | 74.8 |
+| FishAudio S2 | 4B | β
| 0.99 | - | 0.54 | - | 5.99 | - |
+| LongCat-Audio-DiT | 3.5B | β
| 1.50 | 78.6 | 1.09 | 81.8 | 6.04 | 79.7 |
+| **VoxCPM2** | 2B | β
| 1.84 | 75.3 | 0.97 | 79.5 | 8.13 | 75.3 |
+
+
+
+
+### CV3-eval
+
+**CV3-eval Multilingual WER/CER(β¬) Results (click to expand)**
+
+
+| Model | zh | en | hard-zh | hard-en | ja | ko | de | es | fr | it | ru |
+| --------------- | ---- | ---- | ------- | ------- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
+| CosyVoice2 | 4.08 | 6.32 | 12.58 | 11.96 | 9.13 | 19.7 | - | - | - | - | - |
+| CosyVoice3-1.5B | 3.91 | 4.99 | 9.77 | 10.55 | 7.57 | 5.69 | 6.43 | 4.47 | 11.8 | 10.5 | 6.64 |
+| Fish Audio S2 | 2.65 | 2.43 | 9.10 | 4.40 | 3.96 | 2.76 | 2.22 | 2.00 | 6.26 | 2.04 | 2.78 |
+| **VoxCPM2** | 3.65 | 5.00 | 8.55 | 8.48 | 5.96 | 5.69 | 4.77 | 3.80 | 9.85 | 4.25 | 5.21 |
-### CV3-eval
-
-CV3-eval Multilingual WER/CER(β¬) Results (click to expand)
-| Model | zh | en | hard-zh | hard-en | ja | ko | de | es | fr | it | ru |
-|-------|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
-| CosyVoice2 | 4.08 | 6.32 | 12.58| 11.96| 9.13 | 19.7 |- | - | - | - | - |
-| CosyVoice3-1.5B | 3.91 | 4.99 | 9.77 | 10.55 | 7.57 | 5.69 | 6.43 | 4.47 | 11.8 | 10.5 | 6.64 |
-| Fish Audio S2 | 2.65 | 2.43 | 9.10 | 4.40 | 3.96 | 2.76 | 2.22 | 2.00 | 6.26 | 2.04 | 2.78 |
-| **VoxCPM2** | 3.65 | 5.00 | 8.55 | 8.48 | 5.96 | 5.69 | 4.77 | 3.80 | 9.85 | 4.25 | 5.21 |
-
### MiniMax-Multilingual-Test
-
-Minimax-MLS-test WER(β¬) Results (click to expand)
+**Minimax-MLS-test WER(β¬) Results (click to expand)**
-| Language | Minimax | ElevenLabs | Qwen3-TTS | FishAudio S2 | **VoxCPM2** |
-|----------|:-------:|:----------:|:--------------------:|:------------:|:-----------:|
-| Arabic | **1.665** | 1.666 | β | 3.500 | 13.046 |
-| Cantonese | 34.111 | 51.513 | β | **30.670** | 38.584 |
-| Chinese | 2.252 | 16.026 | 0.928 | **0.730** | 1.136 |
-| Czech | 3.875 | **2.108** | β | 2.840 | 24.132 |
-| Dutch | 1.143 | **0.803** | β | 0.990 | 0.913 |
-| English | 2.164 | 2.339 | **0.934** | 1.620 | 2.289 |
-| Finnish | 4.666 | 2.964 | β | 3.330 | **2.632** |
-| French | 4.099 | 5.216 | **2.858** | 3.050 | 4.534 |
-| German | 1.906 | 0.572 | 1.235 | **0.550** | 0.679 |
-| Greek | 2.016 | **0.991** | β | 5.740 | 2.844 |
-| Hindi | 6.962 | **5.827** | β | 14.640 | 19.699 |
-| Indonesian | 1.237 | **1.059** | β | 1.460 | 1.084 |
-| Italian | 1.543 | 1.743 | **0.948** | 1.270 | 1.563 |
-| Japanese | 3.519 | 10.646 | 3.823 | **2.760** | 4.628 |
-| Korean | 1.747 | 1.865 | 1.755 | **1.180** | 1.962 |
-| Polish | 1.415 | **0.766** | β | 1.260 | 1.141 |
-| Portuguese | 1.877 | 1.331 | 1.526 | **1.140** | 1.938 |
-| Romanian | 2.878 | **1.347** | β | 10.740 | 21.577 |
-| Russian | 4.281 | 3.878 | 3.212 | **2.400** | 3.634 |
-| Spanish | 1.029 | 1.084 | 1.126 | **0.910** | 1.438 |
-| Thai | 2.701 | 73.936 | β | 4.230 | 2.961 |
-| Turkish | 1.52 | 0.699 | β | 0.870 | 0.817 |
-| Ukrainian | 1.082 | **0.997** | β | 2.300 | 6.316 |
-| Vietnamese | **0.88** | 73.415 | β | 7.410 | 3.307 |
-
+| Language | Minimax | ElevenLabs | Qwen3-TTS | FishAudio S2 | **VoxCPM2** |
+| ---------- | --------- | ---------- | --------- | ------------ | ----------- |
+| Arabic | **1.665** | 1.666 | β | 3.500 | 13.046 |
+| Cantonese | 34.111 | 51.513 | β | **30.670** | 38.584 |
+| Chinese | 2.252 | 16.026 | 0.928 | **0.730** | 1.136 |
+| Czech | 3.875 | **2.108** | β | 2.840 | 24.132 |
+| Dutch | 1.143 | **0.803** | β | 0.990 | 0.913 |
+| English | 2.164 | 2.339 | **0.934** | 1.620 | 2.289 |
+| Finnish | 4.666 | 2.964 | β | 3.330 | **2.632** |
+| French | 4.099 | 5.216 | **2.858** | 3.050 | 4.534 |
+| German | 1.906 | 0.572 | 1.235 | **0.550** | 0.679 |
+| Greek | 2.016 | **0.991** | β | 5.740 | 2.844 |
+| Hindi | 6.962 | **5.827** | β | 14.640 | 19.699 |
+| Indonesian | 1.237 | **1.059** | β | 1.460 | 1.084 |
+| Italian | 1.543 | 1.743 | **0.948** | 1.270 | 1.563 |
+| Japanese | 3.519 | 10.646 | 3.823 | **2.760** | 4.628 |
+| Korean | 1.747 | 1.865 | 1.755 | **1.180** | 1.962 |
+| Polish | 1.415 | **0.766** | β | 1.260 | 1.141 |
+| Portuguese | 1.877 | 1.331 | 1.526 | **1.140** | 1.938 |
+| Romanian | 2.878 | **1.347** | β | 10.740 | 21.577 |
+| Russian | 4.281 | 3.878 | 3.212 | **2.400** | 3.634 |
+| Spanish | 1.029 | 1.084 | 1.126 | **0.910** | 1.438 |
+| Thai | 2.701 | 73.936 | β | 4.230 | 2.961 |
+| Turkish | 1.52 | 0.699 | β | 0.870 | 0.817 |
+| Ukrainian | 1.082 | **0.997** | β | 2.300 | 6.316 |
+| Vietnamese | **0.88** | 73.415 | β | 7.410 | 3.307 |
-
-Minimax-MLS-test SIM(β¬) Results (click to expand)
-| Language | Minimax | ElevenLabs | Qwen3-TTS | FishAudio S2 | **VoxCPM2** |
-|----------|:-------:|:----------:|:--------------------:|:------------:|:-----------:|
-| Arabic | 73.6 | 70.6 | β | 75.0 | **79.1** |
-| Cantonese | 77.8 | 67.0 | β | 80.5 | **83.5** |
-| Chinese | 78.0 | 67.7 | 79.9 | 81.6 | **82.5** |
-| Czech | 79.6 | 68.5 | β | **79.8** | 78.3 |
-| Dutch | 73.8 | 68.0 | β | 73.0 | **80.8** |
-| English | 75.6 | 61.3 | 77.5 | 79.7 | **85.4** |
-| Finnish | 83.5 | 75.9 | β | 81.9 | **89.0** |
-| French | 62.8 | 53.5 | 62.8 | 69.8 | **73.5** |
-| German | 73.3 | 61.4 | 77.5 | 76.7 | **80.3** |
-| Greek | 82.6 | 73.3 | β | 79.5 | **86.0** |
-| Hindi | 81.8 | 73.0 | β | 82.1 | **85.6** |
-| Indonesian | 72.9 | 66.0 | β | 76.3 | **80.0** |
-| Italian | 69.9 | 57.9 | 81.7 | 74.7 | **78.0** |
-| Japanese | 77.6 | 73.8 | 78.8 | 79.6 | **82.8** |
-| Korean | 77.6 | 70.0 | 79.9 | 81.7 | **83.3** |
-| Polish | 80.2 | 72.9 | β | 81.9 | **88.4** |
-| Portuguese | 80.5 | 71.1 | 81.7 | 78.1 | **83.7** |
-| Romanian | **80.9** | 69.9 | β | 73.3 | 79.7 |
-| Russian | 76.1 | 67.6 | 79.2 | 79.0 | **81.1** |
-| Spanish | 76.2 | 61.5 | 81.4 | 77.6 | **83.1** |
-| Thai | 80.0 | 58.8 | β | 78.6 | **84.0** |
-| Turkish | 77.9 | 59.6 | β | 83.5 | **87.1** |
-| Ukrainian | 73.0 | 64.7 | β | 74.7 | **79.8** |
-| Vietnamese | 74.3 | 36.9 | β | 74.0 | **80.6** |
-
+
+**Minimax-MLS-test SIM(β¬) Results (click to expand)**
+
+
+| Language | Minimax | ElevenLabs | Qwen3-TTS | FishAudio S2 | **VoxCPM2** |
+| ---------- | -------- | ---------- | --------- | ------------ | ----------- |
+| Arabic | 73.6 | 70.6 | β | 75.0 | **79.1** |
+| Cantonese | 77.8 | 67.0 | β | 80.5 | **83.5** |
+| Chinese | 78.0 | 67.7 | 79.9 | 81.6 | **82.5** |
+| Czech | 79.6 | 68.5 | β | **79.8** | 78.3 |
+| Dutch | 73.8 | 68.0 | β | 73.0 | **80.8** |
+| English | 75.6 | 61.3 | 77.5 | 79.7 | **85.4** |
+| Finnish | 83.5 | 75.9 | β | 81.9 | **89.0** |
+| French | 62.8 | 53.5 | 62.8 | 69.8 | **73.5** |
+| German | 73.3 | 61.4 | 77.5 | 76.7 | **80.3** |
+| Greek | 82.6 | 73.3 | β | 79.5 | **86.0** |
+| Hindi | 81.8 | 73.0 | β | 82.1 | **85.6** |
+| Indonesian | 72.9 | 66.0 | β | 76.3 | **80.0** |
+| Italian | 69.9 | 57.9 | 81.7 | 74.7 | **78.0** |
+| Japanese | 77.6 | 73.8 | 78.8 | 79.6 | **82.8** |
+| Korean | 77.6 | 70.0 | 79.9 | 81.7 | **83.3** |
+| Polish | 80.2 | 72.9 | β | 81.9 | **88.4** |
+| Portuguese | 80.5 | 71.1 | 81.7 | 78.1 | **83.7** |
+| Romanian | **80.9** | 69.9 | β | 73.3 | 79.7 |
+| Russian | 76.1 | 67.6 | 79.2 | 79.0 | **81.1** |
+| Spanish | 76.2 | 61.5 | 81.4 | 77.6 | **83.1** |
+| Thai | 80.0 | 58.8 | β | 78.6 | **84.0** |
+| Turkish | 77.9 | 59.6 | β | 83.5 | **87.1** |
+| Ukrainian | 73.0 | 64.7 | β | 74.7 | **79.8** |
+| Vietnamese | 74.3 | 36.9 | β | 74.0 | **80.6** |
+
+
### Internal 30-Language ASR Benchmark
We additionally run an internal multilingual intelligibility benchmark with **30 languages Γ 500 samples**. ASR transcription is evaluated via **Gemini 3.1 Flash Lite API**.
-
-Internal 30-Language ASR Benchmark (click to expand)
+**Internal 30-Language ASR Benchmark (click to expand)**
+
+
+| Language | Metric | VoxCPM2 | Fish S2-Pro |
+| ---------------------- | ------ | --------- | ----------- |
+| ar (Arabic) | CER | 1.23% | 0.30% |
+| da (Danish) | WER | 2.70% | 3.52% |
+| de (German) | WER | 0.96% | 0.64% |
+| el (Greek) | WER | 3.17% | 4.61% |
+| en (English) | WER | 0.42% | 1.03% |
+| es (Spanish) | WER | 1.33% | 0.64% |
+| fi (Finnish) | WER | 2.24% | 2.80% |
+| fr (French) | WER | 2.16% | 2.34% |
+| he (Hebrew) | CER | 2.98% | 15.27% |
+| hi (Hindi) | CER | 0.79% | 0.91% |
+| id (Indonesian) | WER | 1.36% | 1.68% |
+| it (Italian) | WER | 1.65% | 1.08% |
+| ja (Japanese) | CER | 2.40% | 1.82% |
+| km (Khmer) | CER | 2.05% | 75.15% |
+| ko (Korean) | CER | 0.95% | 0.29% |
+| lo (Lao) | CER | 1.90% | 87.40% |
+| ms (Malay) | WER | 1.75% | 1.41% |
+| my (Burmese) | CER | 1.42% | 85.27% |
+| nl (Dutch) | WER | 1.25% | 1.68% |
+| no (Norwegian) | WER | 2.49% | 3.76% |
+| pl (Polish) | WER | 1.90% | 1.65% |
+| pt (Portuguese) | WER | 1.48% | 1.49% |
+| ru (Russian) | WER | 0.90% | 0.86% |
+| sv (Swedish) | WER | 2.22% | 2.63% |
+| sw (Swahili) | CER | 1.07% | 2.02% |
+| th (Thai) | CER | 0.94% | 1.92% |
+| tl (Tagalog) | WER | 2.63% | 4.00% |
+| tr (Turkish) | WER | 1.65% | 1.65% |
+| vi (Vietnamese) | WER | 1.56% | 5.56% |
+| zh (Chinese) | CER | 0.92% | 1.02% |
+| Average (30 languages) | | **1.68%** | - |
+
-| Language | Metric | VoxCPM2 | Fish S2-Pro |
-|---|---:|---:|---:|
-| ar (Arabic) | CER | 1.23% | 0.30% |
-| da (Danish) | WER | 2.70% | 3.52% |
-| de (German) | WER | 0.96% | 0.64% |
-| el (Greek) | WER | 3.17% | 4.61% |
-| en (English) | WER | 0.42% | 1.03% |
-| es (Spanish) | WER | 1.33% | 0.64% |
-| fi (Finnish) | WER | 2.24% | 2.80% |
-| fr (French) | WER | 2.16% | 2.34% |
-| he (Hebrew) | CER | 2.98% | 15.27% |
-| hi (Hindi) | CER | 0.79% | 0.91% |
-| id (Indonesian) | WER | 1.36% | 1.68% |
-| it (Italian) | WER | 1.65% | 1.08% |
-| ja (Japanese) | CER | 2.40% | 1.82% |
-| km (Khmer) | CER | 2.05% | 75.15% |
-| ko (Korean) | CER | 0.95% | 0.29% |
-| lo (Lao) | CER | 1.90% | 87.40% |
-| ms (Malay) | WER | 1.75% | 1.41% |
-| my (Burmese) | CER | 1.42% | 85.27% |
-| nl (Dutch) | WER | 1.25% | 1.68% |
-| no (Norwegian) | WER | 2.49% | 3.76% |
-| pl (Polish) | WER | 1.90% | 1.65% |
-| pt (Portuguese) | WER | 1.48% | 1.49% |
-| ru (Russian) | WER | 0.90% | 0.86% |
-| sv (Swedish) | WER | 2.22% | 2.63% |
-| sw (Swahili) | CER | 1.07% | 2.02% |
-| th (Thai) | CER | 0.94% | 1.92% |
-| tl (Tagalog) | WER | 2.63% | 4.00% |
-| tr (Turkish) | WER | 1.65% | 1.65% |
-| vi (Vietnamese) | WER | 1.56% | 5.56% |
-| zh (Chinese) | CER | 0.92% | 1.02% |
-| Average (30 languages) | | **1.68%** | - |
-
### InstructTTSEval
-
-Instruction-Guided Voice Design Results (click to expand)
-
-| Model | InstructTTSEval-ZH | | | InstructTTSEval-EN | | |
-|-------|:---:|:----:|:----:|:----:|:----:|:----:|
-| | APSβ¬| DSDβ¬ | RPβ¬| APSβ¬ | DSDβ¬ | RPβ¬ |
-| Hume | β | β | β | 83.0 | 75.3 | 54.3 |
-| VoxInstruct | 47.5 | 52.3 | 42.6 | 54.9 | 57.0 | 39.3 |
-| Parler-tts-mini | β | β | β | 63.4 | 48.7 | 28.6 |
-| Parler-tts-large | β | β | β | 60.0 | 45.9 | 31.2 |
-| PromptTTS | β | β | β | 64.3 | 47.2 | 31.4 |
-| PromptStyle | β | β | β | 57.4 | 46.4 | 30.9 |
-| VoiceSculptor | 75.7 | 64.7 | 61.5 | β | β | β |
-| Mimo-Audio-7B-Instruct | 75.7 | 74.3 | 61.5 | 80.6 | 77.6 | 59.5 |
-| Qwen3TTS-12Hz-1.7B-VD | **85.2** | **81.1** | **65.1** | 82.9 | 82.4 | 68.4 |
-| **VoxCPM2** | **85.2** | 71.5 | 60.8 | **84.2** | **83.2** | **71.4** |
-
-
-
+**Instruction-Guided Voice Design Results (click to expand)**
+| Model | InstructTTSEval-ZH | | | InstructTTSEval-EN | | |
+| ---------------------- | ------------------ | -------- | -------- | ------------------ | -------- | -------- |
+| | APS⬠| DSD⬠| RP⬠| APS⬠| DSD⬠| RP⬠|
+| Hume | β | β | β | 83.0 | 75.3 | 54.3 |
+| VoxInstruct | 47.5 | 52.3 | 42.6 | 54.9 | 57.0 | 39.3 |
+| Parler-tts-mini | β | β | β | 63.4 | 48.7 | 28.6 |
+| Parler-tts-large | β | β | β | 60.0 | 45.9 | 31.2 |
+| PromptTTS | β | β | β | 64.3 | 47.2 | 31.4 |
+| PromptStyle | β | β | β | 57.4 | 46.4 | 30.9 |
+| VoiceSculptor | 75.7 | 64.7 | 61.5 | β | β | β |
+| Mimo-Audio-7B-Instruct | 75.7 | 74.3 | 61.5 | 80.6 | 77.6 | 59.5 |
+| Qwen3TTS-12Hz-1.7B-VD | **85.2** | **81.1** | **65.1** | 82.9 | 82.4 | 68.4 |
+| **VoxCPM2** | **85.2** | 71.5 | 60.8 | **84.2** | **83.2** | **71.4** |
@@ -547,30 +529,34 @@ python lora_ft_webui.py # then open http://localhost:7860
Full documentation: **[voxcpm.readthedocs.io](https://voxcpm.readthedocs.io/en/latest/)**
-| Topic | Link |
-|---|---|
-| Quick Start & Installation | [Quick Start](https://voxcpm.readthedocs.io/en/latest/quickstart.html) |
-| Usage Guide & Cookbook | [User Guide](https://voxcpm.readthedocs.io/en/latest/usage_guide.html) |
-| VoxCPM Series | [Models](https://voxcpm.readthedocs.io/en/latest/models/version_history.html) |
-| Fine-tuning (SFT & LoRA) | [Fine-tuning Guide](https://voxcpm.readthedocs.io/en/latest/finetuning/finetune.html) |
-| FAQ & Troubleshooting | [FAQ](https://voxcpm.readthedocs.io/en/latest/faq.html) |
+
+| Topic | Link |
+| -------------------------- | ------------------------------------------------------------------------------------- |
+| Quick Start & Installation | [Quick Start](https://voxcpm.readthedocs.io/en/latest/quickstart.html) |
+| Usage Guide & Cookbook | [User Guide](https://voxcpm.readthedocs.io/en/latest/usage_guide.html) |
+| VoxCPM Series | [Models](https://voxcpm.readthedocs.io/en/latest/models/version_history.html) |
+| Fine-tuning (SFT & LoRA) | [Fine-tuning Guide](https://voxcpm.readthedocs.io/en/latest/finetuning/finetune.html) |
+| FAQ & Troubleshooting | [FAQ](https://voxcpm.readthedocs.io/en/latest/faq.html) |
+
---
## π Ecosystem & Community
-| Project | Description |
-|---|---|
-| [**Nano-vLLM**](https://github.com/a710128/nanovllm-voxcpm) | High-throughput and Fast GPU serving |
-| [**vLLM-Omni**](https://github.com/vllm-project/vllm-omni) | Official vLLM omni-modal serving for VoxCPM2 β PagedAttention, OpenAI-compatible API |
-| [**VoxCPM.cpp**](https://github.com/bluryar/VoxCPM.cpp) | GGML/GGUF: CPU, CUDA, Vulkan inference |
-| [**VoxCPM-ONNX**](https://github.com/bluryar/VoxCPM-ONNX) | ONNX export for CPU inference |
-| [**VoxCPMANE**](https://github.com/0seba/VoxCPMANE) | Apple Neural Engine backend |
-| [**voxcpm_rs**](https://github.com/madushan1000/voxcpm_rs) | Rust re-implementation |
-| [**ComfyUI-VoxCPM**](https://github.com/wildminder/ComfyUI-VoxCPM) | ComfyUI node-based workflows |
-| [**ComfyUI_RH_VoxCPM**](https://github.com/HM-RunningHub/ComfyUI_RH_VoxCPM) | Feature-complete ComfyUI workflow for VoxCPM 2 with multi-speaker generation, LoRA, and auto-ASR |
-| [**ComfyUI-VoxCPMTTS**](https://github.com/1038lab/ComfyUI-VoxCPMTTS) | ComfyUI TTS extension |
-| [**TTS WebUI**](https://github.com/rsxdalv/tts_webui_extension.vox_cpm) | Browser-based TTS extension |
+
+| Project | Description |
+| --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
+| **[Nano-vLLM](https://github.com/a710128/nanovllm-voxcpm)** | High-throughput and Fast GPU serving |
+| **[vLLM-Omni](https://github.com/vllm-project/vllm-omni)** | Official vLLM omni-modal serving for VoxCPM2 β PagedAttention, OpenAI-compatible API |
+| **[VoxCPM.cpp](https://github.com/bluryar/VoxCPM.cpp)** | GGML/GGUF: CPU, CUDA, Vulkan inference |
+| **[VoxCPM-ONNX](https://github.com/bluryar/VoxCPM-ONNX)** | ONNX export for CPU inference |
+| **[VoxCPMANE](https://github.com/0seba/VoxCPMANE)** | Apple Neural Engine backend |
+| **[voxcpm_rs](https://github.com/madushan1000/voxcpm_rs)** | Rust re-implementation |
+| **[ComfyUI-VoxCPM](https://github.com/wildminder/ComfyUI-VoxCPM)** | ComfyUI node-based workflows |
+| **[ComfyUI_RH_VoxCPM](https://github.com/HM-RunningHub/ComfyUI_RH_VoxCPM)** | Feature-complete ComfyUI workflow for VoxCPM 2 with multi-speaker generation, LoRA, and auto-ASR |
+| **[ComfyUI-VoxCPMTTS](https://github.com/1038lab/ComfyUI-VoxCPMTTS)** | ComfyUI TTS extension |
+| **[TTS WebUI](https://github.com/rsxdalv/tts_webui_extension.vox_cpm)** | Browser-based TTS extension |
+
> See the full [Ecosystem](https://voxcpm.readthedocs.io/en/latest/) in the docs. Community projects are not officially maintained by OpenBMB. Built something cool? [Open an issue or PR](https://github.com/OpenBMB/VoxCPM/issues) to add it!
@@ -619,12 +605,8 @@ VoxCPM model weights and code are open-sourced under the [Apache-2.0](LICENSE) l
## Institutions
-
-
ModelBest
-
-
THUHCSI
-
+[ModelBest](https://modelbest.cn/) Β Β Β [THUHCSI](https://github.com/thuhcsi)
## β Star History
-[](https://star-history.com/#OpenBMB/VoxCPM&Date)
+[Star History Chart](https://star-history.com/#OpenBMB/VoxCPM&Date)
\ No newline at end of file