{"data":{"slug":"openbmb-voxcpm","name":"VoxCPM","tagline":"Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning","github_url":"https://github.com/OpenBMB/VoxCPM","owner":"OpenBMB","repo":"VoxCPM","owner_avatar_url":"https://avatars.githubusercontent.com/u/89920203?v=4","primary_language":"Python","stars":34452,"forks":3939,"topics":["audio","deeplearning","minicpm","multilingual","python","pytorch","speech","speech-synthesis","text-to-speech","tts","tts-model","voice-cloning","voice-design","voxcpm"],"archived":false,"github_pushed_at":"2026-07-08T09:46:11+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/openbmb-voxcpm","markdown_url":"https://www.graphcanon.com/tools/openbmb-voxcpm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openbmb-voxcpm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openbmb-voxcpm","description":"VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning","homepage_url":"https://voxcpm.com","license":"Apache-2.0","open_issues":99,"watchers":152,"ai_summary":"VoxCPM2 is a text-to-speech tool capable of multilingual speech generation, voice cloning, and design, featuring tokenizer-free operation.","readme_excerpt":"### Installation\n\n```sh\npip install voxcpm\n```\n\n> **Requirements:** Python ≥ 3.10 (<3.13), PyTorch ≥ 2.5.0, CUDA ≥ 12.0. See [Quick Start Docs](https://voxcpm.readthedocs.io/en/latest/quickstart.html) for details.\n\n---\n\n### 🚢 Production Deployment (Nano-vLLM)\n\nFor high-throughput serving, use **[Nano-vLLM-VoxCPM](https://github.com/a710128/nanovllm-voxcpm)** — a dedicated inference engine built on Nano-vLLM with concurrent request support and an async API.\n\n```bash\npip install nano-vllm-voxcpm\n```\n\n```python\nfrom nanovllm_voxcpm import VoxCPM\nimport numpy as np, soundfile as sf\n\nserver = VoxCPM.from_pretrained(model=\"/path/to/VoxCPM\", devices=[0])\nchunks = list(server.generate(target_text=\"Hello from VoxCPM!\"))\nsf.write(\"out.wav\", np.concatenate(chunks), 48000)\nserver.stop()\n```\n\n> **RTF as low as ~0.13 on NVIDIA RTX 4090** (vs ~0.3 with the standard PyTorch implementation), with support for batched concurrent requests and a FastAPI HTTP server. See the [Nano-vLLM-VoxCPM repo](https://github.com/a710128/nanovllm-voxcpm) for deployment details.\n\n---\n\n# Install from source (latest main — vllm-omni is rapidly evolving)\nuv pip install vllm==0.19.0 --torch-backend=auto\ngit clone https://github.com/vllm-project/vllm-omni.git && cd vllm-omni\nuv pip install -e .\n```\n\nSee the [vLLM-Omni installation guide](https://vllm-omni.readthedocs.io/en/latest/getting_started/installation/) for other platforms (ROCm, XPU, MUSA, NPU) and Docker images.\n\n```bash\n\n---\n\n## 📄 License\n\nVoxCPM model weights and code are open-sourced under the [Apache-2.0](LICENSE) license.","github_created_at":"2025-09-16T03:41:49+00:00","created_at":"2026-07-11T12:03:58.286087+00:00","updated_at":"2026-07-29T06:00:10.651422+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"audio","name":"audio"},{"slug":"deeplearning","name":"deeplearning"},{"slug":"minicpm","name":"minicpm"},{"slug":"multilingual","name":"multilingual"},{"slug":"python","name":"python"},{"slug":"pytorch","name":"pytorch"},{"slug":"speech-synthesis","name":"speech-synthesis"},{"slug":"tts","name":"tts"}],"trust":{"provenance":{"is_fork":false,"github_id":1057664813,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-29T06:00:09.835Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":1,"days_since_push":20,"last_release_at":"2026-05-11T11:59:20Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:04:00.551Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-29T06:00:10.326Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-07-29T06:00:10.326Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-29T06:00:10.326Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-29T06:00:10.326Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["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."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you need to generate high-quality, lifelike voice clones for multiple languages without the overhead of tokenizers.","For applications requiring true-to-life voice design that benefits from tokenizer-free operation for smoother integration into multilingual projects."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:30:08.876Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"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."},{"label":"Adopt for","value":"VoxCPM is a tokenizer-free TTS tool excelling in multilingual speech generation, creative voice design, and lifelike cloning."}]}}