{"data":{"slug":"travisvn-chatterbox-tts-api","name":"chatterbox-tts-api","tagline":"Local OpenAI-compatible text-to-speech API using Chatterbox","github_url":"https://github.com/travisvn/chatterbox-tts-api","owner":"travisvn","repo":"chatterbox-tts-api","owner_avatar_url":"https://avatars.githubusercontent.com/u/2686415?v=4","primary_language":"Python","stars":681,"forks":154,"topics":["ai","chatgpt","chatterbox","cuda","docker","elevenlabs","gpt","local-llm","ollama","open-webui","openai","openai-api","python","self-hosted","speech","text-to-speech","tts","voice-clone","voice-cloning"],"archived":false,"github_pushed_at":"2025-12-23T01:05:47+00:00","maintenance_label":"Slowing","stars_delta_30d":15,"url":"https://www.graphcanon.com/tools/travisvn-chatterbox-tts-api","markdown_url":"https://www.graphcanon.com/tools/travisvn-chatterbox-tts-api.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/travisvn-chatterbox-tts-api","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=travisvn-chatterbox-tts-api","description":"Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)","homepage_url":"https://chatterboxtts.com","license":"AGPL-3.0","open_issues":16,"watchers":10,"ai_summary":"Chatterbox-TTS-API is a self-hosted, Python-based local implementation of an OpenAI-compatible Text-To-Speech service, capable of generating voice-cloned speech on par with ElevenLabs.","readme_excerpt":"## ⚡️ Quick Start\n\n```bash\ngit clone https://github.com/travisvn/chatterbox-tts-api\ncd chatterbox-tts-api\nuv sync\nuv run main.py\n```\n\n> [!TIP]  \n> [uv](https://docs.astral.sh/uv/) installed with `curl -LsSf https://astral.sh/uv/install.sh | sh`\n\n---\n\n### Local Installation with Python 🐍\n\n#### Option A: Using uv (Recommended - Faster & Better Dependencies)\n\n```bash\n\n---\n\n# Install uv if you haven't already\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n---\n\n# Install dependencies with uv (automatically creates venv)\nuv sync\n\n---\n\n# Install dependencies\npip install -r requirements.txt\n\n---\n\n# Clone and start with Docker Compose\ngit clone https://github.com/travisvn/chatterbox-tts-api\ncd chatterbox-tts-api\n\n---\n\n# Use Docker-optimized environment variables\ncp .env.example.docker .env  # Docker-specific paths, ready to use\n\n---\n\n### With Docker Compose Profiles\n\n```bash\n\n---\n\n# Same pattern works with all deployment variants:\ndocker compose -f docker/docker-compose.gpu.yml --profile frontend up -d    # GPU + Frontend\ndocker compose -f docker/docker-compose.uv.yml --profile frontend up -d     # uv + Frontend\ndocker compose -f docker/docker-compose.cpu.yml --profile frontend up -d    # CPU + Frontend\n```\n\n---\n\n### Voice File Requirements\n\n**Supported Formats:**\n\n- MP3 (.mp3)\n- WAV (.wav)\n- FLAC (.flac)\n- M4A (.m4a)\n- OGG (.ogg)\n\n**Requirements:**\n\n- Maximum file size: 10MB\n- Recommended duration: 10-30 seconds of clear speech\n- Avoid background noise for best results\n- Higher quality audio produces better voice cloning\n\n---\n\n# For Docker deployment\ncp .env.example.docker .env\n```\n\nKey environment variables (see the example files for full list):\n\n| Variable                 | Default              | Description                    |\n| ------------------------ | -------------------- | ------------------------------ |\n| `PORT`                   | `4123`               | API server port                |\n| `USE_MULTILINGUAL_MODEL` | `true`               | Enable 23-language support     |\n| `EXAGGERATION`           | `0.5`                | Emotion intensity (0.25-2.0)   |\n| `CFG_WEIGHT`             | `0.5`                | Pace control (0.0-1.0)         |\n| `TEMPERATURE`            | `0.8`                | Sampling randomness (0.05-5.0) |\n| `VOICE_SAMPLE_PATH`      | `./voice-sample.mp3` | Voice sample for cloning       |\n| `DEVICE`                 | `auto`               | Device (auto/cuda/mps/cpu)     |\n\n<details>\n<summary><strong>🎭 Voice Cloning</strong></summary>\n\nReplace the default voice sample:\n\n```bash\n\n---\n\n# Full Stack mode with UI (using Docker)\npython start.py fullstack\n\n---\n\n# Install in development mode (pip)\npip install -e .","github_created_at":"2025-05-31T20:44:03+00:00","created_at":"2026-07-15T10:59:11.181106+00:00","updated_at":"2026-09-20T05:01:55.215208+00:00","categories":[{"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":"ai","name":"ai"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"chatterbox","name":"chatterbox"},{"slug":"cuda","name":"cuda"},{"slug":"docker","name":"docker"},{"slug":"elevenlabs","name":"elevenlabs"},{"slug":"openai-api","name":"openai-api"},{"slug":"self-hosted","name":"self-hosted"}],"trust":{"provenance":{"is_fork":false,"github_id":993931907,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:01:52.761Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":271,"last_release_at":null,"stars_delta_30d":15,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:59:12.441Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:01:53.806Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T05:01:53.806Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-09-20T05:01:53.806Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires a local setup environment that supports CUDA for optimal performance; Docker can simplify deployment."]},"constraints":null,"when_to_use":["When you need a self-hosted solution that mirrors the functionality of ElevenLabs or other proprietary TTS services and requires compatibility with existing ecosystems like Open WebUI or AnythingLLM.","If your project demands local processing to avoid data privacy concerns related to cloud-based text-to-speech platforms."],"when_not_to_use":["If you require integrations specific to ElevenLabs' proprietary voice models as Chatterbox-TTS-API, despite its capabilities, does not directly support their unique voice libraries.","For users needing a fully managed service without the complexities of local deployment and maintenance, like that offered by cloud-based TTS providers."],"source":"enrich:decision_facts","observed_at":"2026-07-17T11:05:05.482Z"},"constraint_facets":null,"decision_summary":[{"label":"Requirements","value":"Requires a local setup environment that supports CUDA for optimal performance; Docker can simplify deployment."},{"label":"Adopt for","value":"Chatterbox-TTS-API is a locally hosted Python-based text-to-speech API with capabilities similar to ElevenLabs, offering an OpenAI-compatible interface for generating voice-cloned speech."},{"label":"License detail","value":"Chatterbox-TTS-API is distributed under the AGPL-3.0 license, ensuring any modifications or derivative works must be shared openly."}]}}