{"data":{"slug":"devnen-chatterbox-tts-server","name":"Chatterbox-TTS-Server","tagline":"Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale te","github_url":"https://github.com/devnen/Chatterbox-TTS-Server","owner":"devnen","repo":"Chatterbox-TTS-Server","owner_avatar_url":"https://avatars.githubusercontent.com/u/195903272?v=4","primary_language":"Python","stars":1348,"forks":323,"topics":["ai","api-server","audio-generation","chatterbox","chatterbox-tts","cuda","fastapi","huggingface","openai-api","python","pytorch","rocm","speech-synthesis","speech-synthesis-api","text-to-speech","tts","tts-api","voice-cloning","web-ui"],"archived":false,"github_pushed_at":"2026-05-26T19:49:30+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/devnen-chatterbox-tts-server","markdown_url":"https://www.graphcanon.com/tools/devnen-chatterbox-tts-server.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/devnen-chatterbox-tts-server","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=devnen-chatterbox-tts-server","description":"Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.","homepage_url":"https://colab.research.google.com/github/devnen/Chatterbox-TTS-Server/blob/main/Chatterbox_TTS_Colab_Demo.ipynb","license":"MIT","open_issues":43,"watchers":11,"ai_summary":null,"readme_excerpt":"### 🖥️ Installation fixes across all platforms\n\n- **All platforms:** Chatterbox is now installed with `--no-deps` across all installation paths (CPU, NVIDIA, cu128, ROCm). This eliminates ONNX source build failures, torch version conflicts, and CMake errors that affected many users. Chatterbox's dependencies (conformer, diffusers, transformers, s3tokenizer, etc.) are now listed explicitly in each requirements file with `onnx==1.16.0` pinned to guarantee pre-built wheels.\n- **Apple Silicon / MPS:** Fixed Turbo model crash (\"Cannot convert a MPS Tensor to float64 dtype\") by forcing float32 in s3tokenizer and voice_encoder. Fix applied in the chatterbox-v2 fork and also as an automatic post-install patch in `start.py` for users of other chatterbox versions. Thanks to @jonas3245 (#93).\n- **Docker CPU:** New lightweight `Dockerfile.cpu` based on `python:3.10-slim` instead of the 4GB+ NVIDIA CUDA base image. `docker-compose-cpu.yml` now uses this smaller image. Removed deprecated `version` tags from all docker-compose files.\n- **config.yaml:** Default device changed from `cuda` to `auto` for correct auto-detection on all hardware (CUDA, MPS, CPU).\n- **Python version:** **Python 3.10 is required** — it is the only version with pre-built wheels for all dependencies (torch, torchvision, ONNX). Python 3.11+ may fail due to missing wheels. The Windows launcher's Portable Mode handles this automatically by using an embedded Python 3.10 runtime.\n- **Blackwell (CUDA 12.8):** Fixed `requirements-nvidia-cu128.txt` to properly install PyTorch 2.9.0 with CUDA 12.8 (`sm_120` support) for RTX 5060 Ti, 5070, 5070 Ti, 5080, and 5090 GPUs. The `Dockerfile.cu128` now correctly installs chatterbox with `--no-deps` to prevent PyTorch downgrade.\n- **AMD ROCm:** Fixed ROCm installation by switching to PyTorch's official ROCm 6.1 wheel index (`torch==2.5.1+rocm6.1`), which resolves the previous `torch==2.6.0` / `torchaudio==2.5.1` version conflict. A new `requirements-rocm-init.txt` installs the ROCm PyTorch stack before other dependencies. Both `Dockerfile.rocm` and `start.py` now use a two-step install to prevent pip from replacing ROCm torch wheels with CPU-only versions.\n- Thanks to community contributors in issues #20, #23, #44, #58, #64, #79, #89, #92, #93, #98, #105, #107, #109, #113, #114, #121, and #122 for testing and reporting solutions.\n\n---\n\n### Hardware Compatibility Matrix\n\n| Hardware | Installation Option | Requirements File | Driver Requirement |\n|----------|--------------------|--------------------|-------------------|\n| CPU Only | `--cpu` | requirements.txt | None |\n| NVIDIA RTX 20/30/40 | `--nvidia` | requirements-nvidia.txt | 525+ |\n| NVIDIA RTX 5090 / Blackwell (sm_120) | `--nvidia-cu128` | requirements-nvidia-cu128.txt (torch 2.9, CUDA 12.8) | 570+ |\n| NVIDIA DGX Spark / GB10 (sm_121) | Docker only | requirements-nvidia-cu130.txt (torch 2.10, CUDA 13.0) | 580+ |\n| AMD RX 6000/7000 (Linux) | `--rocm` | requirements-rocm.txt | ROCm 6.4+ |\n| AMD Strix Halo (Ryzen AI MAX+) | Docker only | requirements-strixhalo.txt (ROCm 7.2) | ROCm 7.2+ |\n| AMD RX 9000 series / RDNA4 (Linux) | Docker only | requirements-rdna4-init.txt (ROCm 7.2) | ROCm 7.2+ |\n| Apple Silicon (M1/M2/M3/M4) | Manual install | See Option 4 | macOS 12.3+ |\n\n---\n\n---\n\n## 💻 Installation and Setup\n\nThis project uses specific dependency files to ensure a smooth installation for your hardware. You can choose between the **automated launcher** (recommended for most users) or **manual installation** (for advanced users).\n\n**1. Clone the Repository**\n```bash\ngit clone https://github.com/devnen/Chatterbox-TTS-Server.git\ncd Chatterbox-TTS-Server\n```\n\n---\n\n---\n\n### 🚀 Quick Start with Automated Launcher (Recommended)\n\nThe automated launcher handles virtual environment creation, hardware detection, dependency installation, and server startup - all in one step.\n\n#### Windows\n\n```bash\n\n---\n\n# Skip menu and install NVIDIA CUDA 12.1 directly\npython start.py --nvidia\n\n---\n\n# Upgrade to l","github_created_at":"2025-05-31T12:38:24+00:00","created_at":"2026-07-11T12:12:03.377869+00:00","updated_at":"2026-07-11T12:12:16.874369+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"},{"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"}],"tags":[{"slug":"audio-generation","name":"audio-generation"},{"slug":"api-server","name":"api-server"},{"slug":"ai","name":"ai"},{"slug":"cuda","name":"cuda"},{"slug":"fastapi","name":"fastapi"},{"slug":"chatterbox-tts","name":"chatterbox-tts"},{"slug":"chatterbox","name":"chatterbox"},{"slug":"huggingface","name":"huggingface"}],"trust":{"provenance":{"is_fork":false,"github_id":993746345,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:12:04.065Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":1,"days_since_push":45,"last_release_at":"2026-05-11T15:04:48Z"},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":95,"high_count":0,"last_scan_at":"2026-07-11T12:12:11.620Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:12:11.174Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-11T12:12:11.174Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T12:12:11.174Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-11T12:12:11.174Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T12:12:11.174Z"}}}}