--- title: "CosyVoice vs VoxCPM" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/funaudiollm-cosyvoice-vs-openbmb-voxcpm" tools: ["funaudiollm-cosyvoice", "openbmb-voxcpm"] --- # CosyVoice vs VoxCPM *GraphCanon updated Aug 23, 2026* ## Verdict Pick CosyVoice if cosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation; pick VoxCPM if voxCPM is a tokenizer-free TTS tool excelling in multilingual speech generation, creative voice design, and lifelike cloning. [CosyVoice](https://funaudiollm.github.io/cosyvoice3) reports 23k GitHub stars, 2.6k forks, and 719 open issues, last pushed May 25, 2026. [VoxCPM](https://voxcpm.com) has 34k stars, 3.9k forks, and 99 open issues, last pushed Jul 8, 2026. Figures are from public GitHub metadata via [CosyVoice's repository](https://github.com/FunAudioLLM/CosyVoice) and [VoxCPM's repository](https://github.com/OpenBMB/VoxCPM). | | [CosyVoice](/tools/funaudiollm-cosyvoice.md) | [VoxCPM](/tools/openbmb-voxcpm.md) | | --- | --- | --- | | Tagline | Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment. | Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning | | Stars | 22,870 | 34,452 | | Forks | 2,631 | 3,939 | | Open issues | 719 | 99 | | Language | Python | Python | | Adopt for | CosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation. | VoxCPM is a tokenizer-free TTS tool excelling in multilingual speech generation, creative voice design, and lifelike cloning. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | Inference & Serving, Model Training, Speech & Audio | Inference & Serving, Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CosyVoice](/tools/funaudiollm-cosyvoice.md) | [VoxCPM](/tools/openbmb-voxcpm.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Active (82%) | | Days since push | 89d | 20d | | Open issues (now) | 719 | 99 | | Stars delta | +497 (30d) | Unknown | | Open issues delta | -37 (30d) | Unknown | | Full report | [trust report](/tools/funaudiollm-cosyvoice/trust.md) | [trust report](/tools/openbmb-voxcpm/trust.md) | ## Shared compatibility - **Python**: [CosyVoice](/tools/funaudiollm-cosyvoice.md) - Python runtime; [VoxCPM](/tools/openbmb-voxcpm.md) - Python runtime ## Decision facts: CosyVoice - **Adopt for:** CosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation. ## Decision facts: VoxCPM - **Requirements:** Python >= 3.10 (<3.13), PyTorch >= 2.5.0, CUDA >= 12.0.; For production deployment, Nano-vLLM is recommended for its high throughput and concurrent request support. - **Adopt for:** VoxCPM is a tokenizer-free TTS tool excelling in multilingual speech generation, creative voice design, and lifelike cloning. ## Choose when ### Choose CosyVoice if… - Tags unique to CosyVoice: audio-generation, cantonese, chatbot, chatgpt. - Also covers Model Training. - When you need support for multiple languages like Cantonese, Chinese, English, Japanese, and Korean. ### Choose VoxCPM if… - Requirements: Python >= 3.10 (<3.13), PyTorch >= 2.5.0, CUDA >= 12.0.; For production deployment, Nano-vLLM is recommended for its high throughput and concurrent request support.. - Tags unique to VoxCPM: audio, deeplearning, minicpm, multilingual. - When you need to generate high-quality, lifelike voice clones for multiple languages without the overhead of tokenizers. ## When NOT to use CosyVoice - If your project specifically requires fine-tuned performance in languages not supported by CosyVoice such as Arabic or Spanish. - When strict real-time speech synthesis requirements are essential, as CosyVoice may face delays depending on the environment's computational power and model complexity. ## When NOT to use VoxCPM - If your project is constrained by hardware with less powerful GPUs than NVIDIA RTX 4090, as VoxCPM might not provide optimal real-time factor performance. - When a simple text-to-speech solution suffices and does not require the advanced features like voice cloning or creative voice design that VoxCPM offers. ## Common questions ### What is the difference between CosyVoice and VoxCPM? CosyVoice: Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment.. VoxCPM: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning. See the comparison table for live GitHub stats and shared categories. ### When should I choose CosyVoice over VoxCPM? Choose CosyVoice over VoxCPM when Tags unique to CosyVoice: audio-generation, cantonese, chatbot, chatgpt; Also covers Model Training; When you need support for multiple languages like Cantonese, Chinese, English, Japanese, and Korean. ### When should I choose VoxCPM over CosyVoice? Choose VoxCPM over CosyVoice when Requirements: Python >= 3.10 (<3.13), PyTorch >= 2.5.0, CUDA >= 12.0.; For production deployment, Nano-vLLM is recommended for its high throughput and concurrent request support.; Tags unique to VoxCPM: audio, deeplearning, minicpm, multilingual; When you need to generate high-quality, lifelike voice clones for multiple languages without the overhead of tokenizers. ### When should I avoid CosyVoice? If your project specifically requires fine-tuned performance in languages not supported by CosyVoice such as Arabic or Spanish. When strict real-time speech synthesis requirements are essential, as CosyVoice may face delays depending on the environment's computational power and model complexity. ### When should I avoid VoxCPM? If your project is constrained by hardware with less powerful GPUs than NVIDIA RTX 4090, as VoxCPM might not provide optimal real-time factor performance. When a simple text-to-speech solution suffices and does not require the advanced features like voice cloning or creative voice design that VoxCPM offers. ### Is CosyVoice or VoxCPM more popular on GitHub? VoxCPM has more GitHub stars (34,452 vs 22,870). Stars measure visibility, not whether either tool fits your constraints. ### Are CosyVoice and VoxCPM open source? Yes - both are open-source projects on GitHub (CosyVoice: Apache-2.0, VoxCPM: Apache-2.0). ### Where can I find alternatives to CosyVoice or VoxCPM? GraphCanon lists graph-backed alternatives at [CosyVoice alternatives](/tools/funaudiollm-cosyvoice/alternatives) and [VoxCPM alternatives](/tools/openbmb-voxcpm/alternatives) ([CosyVoice markdown twin](/tools/funaudiollm-cosyvoice/alternatives.md), [VoxCPM markdown twin](/tools/openbmb-voxcpm/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/funaudiollm-cosyvoice-vs-openbmb-voxcpm.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, CosyVoice or VoxCPM? CosyVoice: Steady. VoxCPM: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for CosyVoice and VoxCPM? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [CosyVoice trust report](/tools/funaudiollm-cosyvoice/trust); [VoxCPM trust report](/tools/openbmb-voxcpm/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=funaudiollm-cosyvoice`](/api/graphcanon/graph?tool=funaudiollm-cosyvoice) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_