OpenBMB /VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
★ 42,520⑂ 4,861👁 164⑃ 117● 341▤ 14
Download: v2.0.3: fine-tuning validation, runtime stability, and streaming improvementsv2.0.3 ↓2.0.32026-05-11
+41
Daily
+548
Weekly
+3,360
Monthly
42,520
stars
4,861
forks
164
watchers
117
prs
341
issues
14
releases
README
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
English | 中文
👋 Join our community for discussion and support!
Feishu
|
Discord
|
📚 MiniCPM Wiki
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.
VoxCPM2 is the latest major release — a 2B parameter model trained on over 2 million hours of multilingual speech data, now supporting 30 languages, Voice Design, Controllable Voice Cloning, and 48kHz studio-quality audio output. Built on a MiniCPM-4 backbone.
✨ Highlights
- 🌍 30-Language Multilingual — Input text in any of the 30 supported languages and synthesize directly, no language tag needed
- 🎨 Voice Design — Create a brand-new voice from a natural-language description alone (gender, age, tone, emotion, pace …), no reference audio required
- 🎛️ Controllable Cloning — Clone any voice from a short reference clip, with optional style guidance to steer emotion, pace, and expression while preserving the original timbre
- 🎙️ Ultimate Cloning — Reproduce every vocal nuance: provide both reference audio and its transcript, and the model continues seamlessly from the reference, faithfully preserving every vocal detail — timbre, rhythm, emotion, and style (same as VoxCPM1.5)
- 🔊 48kHz High-Quality Audio — Accepts 16kHz reference audio and directly outputs 48kHz studio-quality audio via AudioVAE V2's asymmetric encode/decode design, with built-in super-resolution — no external upsampler needed
- 🧠 Context-Aware Synthesis — Automatically infers appropriate prosody and expressiveness from text content
- ⚡ Real-Time Streaming — RTF as low as ~0.3 on NVIDIA RTX 4090, and ~0.13 accelerated by Nano-vLLM or vLLM-Omni — official vLLM omni-modal serving for VoxCPM2 with PagedAttention and an OpenAI-compatible API
- 📜 Fully Open-Source & Commercial-Ready — Weights and code released under the Apache-2.0 license, free for commercial use
🌍 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: 四川话, 粤语, 吴语, 东北话, 河南话, 陕西话, 山东话, 天津话, 闽南话
News
- [2026.04] 🔥 We release VoxCPM2 — 2B, 30 languages, Voice Design & Controllable Voice Cloning, 48kHz audio output! Weights | Docs | Playground | Technical Report
- [2025.12] 🎉 Open-source VoxCPM1.5 weights with SFT & LoRA fine-tuning. (🏆 1 GitHub Trending)
- [2025.09] 🔥 Release VoxCPM Technical Report.
- [2025.09] 🎉 Open-source VoxCPM-0.5B weights (🏆 1 HuggingFace Trending)
---
Contents
- Quick Start
- InstallatioTop issues
#213Voice cutoff at the end of words — Polish language52 comments · 2026-04-08#15Finetune New Language?15 comments · 2025-09-19#114Info on finetune scripts14 comments · 2025-12-10#357Hallucination on very short standalone utterances (single-word Polish sentences: "tak"/"nie"/"ja")11 comments · 2026-07-13#244A Cut-off Result or Distortion Sound11 comments · 2026-04-11#101ADD A NEW LANGUAGE10 comments · 2025-12-07#335我这边是使用4张3090 24G显存共96G显存利用Voxcpm2进行微调,官方全参数微调硬件说明40G显存就能搞定,但是我这边完全无法进行,老是报显存溢出9 comments · 2026-06-08#308lora微调训练的时候指定了ref_audio,infer的时候怎么用这个ref_audio?9 comments · 2026-05-18
Latest release
v2.0.3: fine-tuning validation, runtime stability, and streaming improvements 2.0.3 2026-05-11VoxCPM v2.0.3 This release focuses on fine-tuning usability, runtime stability, safer LoRA loading, and faster streaming inference. Highlights - Added voxcpm validate for pre-flight JSONL training manifest validation. - Added optional ref_audio support in the fine-tuning data pipeline. - Improved runtime device handling with explicit --device support and safer MPS dtype behavior. - Improved VoxCPM2 streaming VAE decoding by avoiding redundant overlap decoding. - Hardened legacy LoRA checkpoint loading with weights_only=True. - Fixed LoRA rank mismatch handling in lora_ft_webui.py. New Fe
相关报道 (12)
blog.csdnGitHub 开源项目解析:OpenBMB/VoxCPM —— Tokenizer-Free 多语言语音合成与声音克隆模型2026-06-02DoNewsVoxCPM 1.5正式开源,语音生成全面升级2025-12-11IT之家面壁智能 VoxCPM 1.5 语音生成 AI 模型开源:高采样音频克隆,生成效率翻倍2025-12-10blog.csdn【GitHub项目推荐--VoxCPM:无分词器TTS与真实语音克隆完全指南】2025-09-20news.futunn面壁智能:發佈語音生成基座模型VoxCPM2025-09-18腾讯网面壁智能发布语音生成基座模型VoxCPM:0.5B参数号称媲美真人2025-09-18腾讯网面壁智能发布语音生成基座模型VoxCPM,称可媲美真人、能用方言2025-09-18东方财富网面壁智能:发布语音生成基座模型VoxCPM2025-09-18智源社区张雪机车燃爆封神!国产2B语音模型重磅开源,全网听完都起鸡皮疙瘩2026-04-09腾讯新闻AI 语音赛道的角逐,可能已经结束了2026-04-08
News & coverage (4)
Hacker NewsVoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and Voice Cloning▲ 3 · 0 comments · 2025-12-05noteVoxCPM: Speech Synthesis Without Tokenizers - The Technology of Designing and Cloning Voices and the Remaining Risks2026-11-05YouTubeVoxCPM 2 Review + Tutorial - 2026 | Make Human AI Voice Cloning With Emotions2026-05-06MediumVoxCPM2: The Open-Source Voice Model That Beats ElevenLabs on Similarity — But the Full Benchmark…2026-04-12