{"data":{"slug":"remsky-kokoro-fastapi","name":"Kokoro-FastAPI","tagline":"Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model","github_url":"https://github.com/remsky/Kokoro-FastAPI","owner":"remsky","repo":"Kokoro-FastAPI","owner_avatar_url":"https://avatars.githubusercontent.com/u/25017870?v=4","primary_language":"Python","stars":5461,"forks":902,"topics":["fastapi","kokoro","kokoro-82m","kokoro-tts","multi-speaker-tts","mutilingual-audio","openai-compatible-api","openwebui","pytorch","read-along","sillytavern","ssml","text-to-speech","tts","tts-api","tts-captions","tts-generation","voice-clone-tool"],"archived":false,"github_pushed_at":"2026-09-10T05:45:23+00:00","maintenance_label":"Active","stars_delta_30d":196,"url":"https://www.graphcanon.com/tools/remsky-kokoro-fastapi","markdown_url":"https://www.graphcanon.com/tools/remsky-kokoro-fastapi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/remsky-kokoro-fastapi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=remsky-kokoro-fastapi","description":"Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, optional readalong web UI","homepage_url":null,"license":"Apache-2.0","open_issues":13,"watchers":36,"ai_summary":"Repository hosts Docker images and Python scripts that wrap the Kokoro-82M text-to-speech model using FastAPI.","readme_excerpt":"<br>\n\n<a href=\"https://trendshift.io/repositories/13745?utm_source=repository-badge&amp;utm_medium=badge&amp;utm_campaign=badge-repository-13745\"><img src=\"https://trendshift.io/api/badge/repositories/13745\" alt=\"remsky%2FKokoro-FastAPI | Trendshift\" width=\"164\" height=\"36\"/></a>\n\n\n \n\n\n\n \n\n \n\n\nDockerized FastAPI wrapper for [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) text-to-speech model. Generate hours of high quality speech in minutes.\n\n- OpenAI-compatible Speech endpoint, multi-language support\n  - English (US/GB), Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, Mandarin Chinese\n- Custom voicepack generation via [Inno Clone-Tuner](https://github.com/remsky/inno-kokoro)\n- Optional integrated WebUI; read-along long-generation\n- Inline multi-speaker generation & voice mixing + aliasing weighted combinations, SSML support\n- Per-word, or per-chunk timestamped caption generation\n- Phoneme endpoints: generate phonemes from text, or generate audio from phonemes\n- Prebuilt multiplatform images\n  - CPU and NVIDIA GPU (CUDA): linux/amd64 + linux/arm64\n  - AMD GPU (ROCm, experimental): linux/amd64 only\n- Apple Silicon (MPS) supported when running directly via UV (no image)\n\n\n### Integration & Guides \n \n\n   \n\n\nCommunity projects that use, recommend, or enable Kokoro-FastAPI as a backend:\n\n- <sub>Home Assistant: [wyoming_openai](https://github.com/roryeckel/wyoming_openai), [openai_tts](https://github.com/sfortis/openai_tts), [Kokoro-TTS](https://github.com/beecho01/Kokoro-TTS)</sub>\n- <sub>App stores and templates: [Umbrel](https://github.com/getumbrel/umbrel-apps/tree/master/kokoro), [Unraid Apps](https://github.com/nwithan8/unraid_templates), [GPUStack](https://github.com/gpustack/gpustack), [jetson-containers](https://github.com/dusty-nv/jetson-containers/tree/master/packages/speech/kokoro-tts)</sub>\n- <sub>Readers and audiobooks: [openreader](https://github.com/richardr1126/openreader), [epub_to_audiobook](https://github.com/p0n1/epub_to_audiobook), [audiobook-creator](https://github.com/prakharsr/audiobook-creator), [Zotero-TTS](https://github.com/xujialiu/Zotero-TTS)</sub>\n- <sub>Assistants and agents: [xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server), [call-me](https://github.com/ZeframLou/call-me), [agent-cli](https://github.com/basnijholt/agent-cli), [voice-chat-ai](https://github.com/bigsk1/voice-chat-ai)</sub>\n- <sub>Browser: [kokoro-extension](https://github.com/Fooftilly/kokoro-extension), [customtts](https://github.com/BassGaming/customtts)</sub>\n\n## Get Started\n\n<details>\n<summary>Quickest Start (docker run)</summary>\n\nPre-built multi-arch images with models baked in. \n\n`:latest` is available, but please pin to a release tag for stable usage.\n\n<sub><ins>**No GPU**</ins> (laptop, CPU-only server)</sub>\n```bash\ndocker run -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-cpu:latest\n```\n\n<sub><ins>**NVIDIA**</ins> (GTX 900-series through RTX 40; ships cu126)</sub>\n```bash\ndocker run --gpus all -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-gpu:latest\n```\n\n<sub><ins>**NVIDIA RTX 50-series / Blackwell**</ins> (ships cu128)</sub>\n```bash\ndocker run --gpus all -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-gpu:latest-cu128\n```\n\n<sub><ins>**NVIDIA arm64**</ins> (Jetson, GH200; same tag, ships cu129)</sub>\n```bash\ndocker run --gpus all -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-gpu:latest\n```\n\n<sub><ins>**AMD GPU**</ins> (ROCm, experimental, x86_64 only)</sub>\n```bash\ndocker run --device=/dev/kfd --device=/dev/dri -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-rocm:latest\n```\n\n<sub><ins>**Apple Silicon**</ins> (native MPS clone; the CPU image also works)</sub>\n```bash\n./start-gpu_mac.sh\n```\n\n`gpu:latest` is the same image as `gpu:latest-cu126`. Configuration via environment variables, see [the configuration guide](docs/configuration.md).\n\n</details>\n\n<details>\n\n<summary>Quick Start (docker compose) </summary>\n\n1. Install prerequisites, and start the service using Docker Compose (Full setup inclu","github_created_at":"2024-12-30T11:53:42+00:00","created_at":"2026-07-11T12:06:28.423955+00:00","updated_at":"2026-09-20T07:05:54.831891+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":"docker","name":"docker"},{"slug":"fastapi","name":"fastapi"},{"slug":"kokoro-tts","name":"kokoro tts"},{"slug":"multi-gpu-support","name":"multi-gpu support"},{"slug":"openai-compatible-api","name":"openai-compatible-api"},{"slug":"pytorch","name":"pytorch"},{"slug":"text-to-speech","name":"text-to-speech"}],"trust":{"provenance":{"is_fork":false,"github_id":910061041,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:05:52.082Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":8,"days_since_push":10,"last_release_at":"2026-09-10T05:05:52Z","stars_delta_30d":196,"open_issues_delta_30d":-96},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:06:30.690Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T07:05:53.139Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:05:53.139Z"},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-09-20T07:05:53.139Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T07:05:53.139Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Hardware-specific Docker images are provided for CUDA, ROCm (experimental), and CPU support.","Users without supported GPUs can still utilize the service via a CPU image."],"min_ram_gb":4,"requires_docker":true},"constraints":{"min_ram_gb":4,"requires_docker":true},"when_to_use":["You require a solution that can auto-download models and run natively on Apple Silicon (MPS) with support via UV.","Your project needs an open-source text-to-speech model endpoint compatible with OpenAI, supporting multi-language audio synthesis."],"when_not_to_use":["If your hardware is not supported by the provided Docker images, for example, if you do not have a compatible NVIDIA, AMD GPU or CPU setup.","You are looking for non-Dockerized solutions. Kokoro-FastAPI focuses on containerization and might not fit environments that strictly avoid containers."],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:16:48.949Z"},"constraint_facets":{"min_ram_gb":4,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Min 4 GB RAM; Requires Docker; Hardware-specific Docker images are provided for CUDA, ROCm (experimental), and CPU support.; Users without supported GPUs can still utilize the service via a CPU image."},{"label":"Adopt for","value":"Kokoro-FastAPI is a Dockerized wrapper for the Kokoro-82M text-to-speech model using FastAPI. It supports multi-language capability and provides prebuilt images for various hardware types."}]}}