{"data":{"slug":"denizsafak-abogen","name":"abogen","tagline":"Generate audiobooks from EPUBs, PDFs and text with synchronized captions.","github_url":"https://github.com/denizsafak/abogen","owner":"denizsafak","repo":"abogen","owner_avatar_url":"https://avatars.githubusercontent.com/u/39929354?v=4","primary_language":"Python","stars":6025,"forks":466,"topics":["audiobook","audiobooks","content-creation","content-creator","ebook","epub","epub-converter","kokoro","kokoro-82m","kokoro-tts","llm","media-generation","narrator","speech-synthesis","subtitles","text-to-audio","text-to-speech","tts","voice-conversion","voice-synthesis"],"archived":false,"github_pushed_at":"2026-09-07T14:30:10+00:00","maintenance_label":"Active","stars_delta_30d":596,"url":"https://www.graphcanon.com/tools/denizsafak-abogen","markdown_url":"https://www.graphcanon.com/tools/denizsafak-abogen.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/denizsafak-abogen","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=denizsafak-abogen","description":"Generate audiobooks from EPUBs, PDFs and text with synchronized captions.","homepage_url":"https://pypi.org/project/abogen/","license":"MIT","open_issues":48,"watchers":31,"ai_summary":"abogen is an open-source tool for generating audiobooks with synchronized captions from ebooks and other textual formats using speech synthesis technologies like Kokoro TTS system and espeak-ng.","readme_excerpt":"## `How to install?` \"Abogen\n\n---\n\n# Install abogen\npip install abogen\n```\n\n\n\n---\n\n# Install espeak-ng\nbrew install espeak-ng\n\n---\n\n# After installing abogen, we need to install Kokoro's development version which includes MPS support.\npip3 install git+https://github.com/hexgrad/kokoro.git\n```\n\n\n\n---\n\n# Install espeak-ng\nsudo apt install espeak-ng # Ubuntu/Debian\nsudo pacman -S espeak-ng # Arch Linux\nsudo dnf install espeak-ng # Fedora\n\n---\n\n# Already supported, no need to install CUDA separately.\n\n---\n\n### Docker Compose (GPU by default)\nThe repo includes `docker-compose.yaml`, which targets GPU hosts out of the box. Install the NVIDIA Container Toolkit and run:\n\n```bash\ndocker compose up -d --build\n```\n\nKey build/runtime knobs:\n\n- `TORCH_VERSION` – pin a specific PyTorch release that matches your driver (leave blank for the latest on the configured index).\n- `TORCH_INDEX_URL` – swap out the PyTorch download index when targeting a different CUDA build.\n- `ABOGEN_DATA` – host path that stores uploads/outputs (defaults to `./data`).\n\nCPU-only deployment: comment out the `deploy.resources.reservations.devices` block (and the optional `runtime: nvidia` line) inside the compose file. Compose will then run without requesting a GPU. If you prefer the classic CLI:\n\n```bash\ndocker build -f abogen/Dockerfile -t abogen-gpu .\ndocker run --rm \\\n --gpus all \\\n -p 8808:8808 \\\n -v ~/abogen-data:/data \\\n abogen-gpu\n```\n\n---\n\n# 🇯🇵 'j' => Japanese: pip install misaki[ja]\n\n---\n\n# 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh]\n```\nFor a complete list of supported languages and voices, refer to Kokoro's [VOICES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md). To listen to sample audio outputs, see [SAMPLES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/SAMPLES.md).\n\n> See [How to fix Japanese audio not working?](#japanese-audio-not-working)\n\n---\n\n---\n\n## `License`\nThis project is available under the MIT License - see the [LICENSE](https://github.com/denizsafak/abogen/blob/main/LICENSE) file for details.\n[Kokoro](https://github.com/hexgrad/kokoro) is licensed under [Apache-2.0](https://github.com/hexgrad/kokoro/blob/main/LICENSE) which allows commercial use, modification, distribution, and private use.","github_created_at":"2025-04-24T01:06:05+00:00","created_at":"2026-07-11T12:06:33.146591+00:00","updated_at":"2026-09-20T07:06:02.985465+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"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":"audiobook","name":"audiobook"},{"slug":"content-creation","name":"content-creation"},{"slug":"epub","name":"epub"},{"slug":"pdf","name":"pdf"},{"slug":"speech-synthesis","name":"speech-synthesis"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"tts","name":"tts"},{"slug":"voice-conversion","name":"voice-conversion"}],"trust":{"provenance":{"is_fork":false,"github_id":971726597,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:06:00.357Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":12,"last_release_at":"2026-02-06T21:04:50Z","stars_delta_30d":596,"open_issues_delta_30d":3},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:06:39.425Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:06:01.413Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T07:06:01.413Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T07:06:01.413Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T07:06:01.413Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You require comprehensive support for both English and non-English voices, including Japanese and Mandarin Chinese","You need a tool that supports GPU acceleration via Docker with the NVIDIA Container Toolkit"],"when_not_to_use":["For use cases requiring minimal setup without the need to install Kokoro's development version or espeak-ng separately","If your project strictly limits external dependencies to pre-installed packages, as abogen requires additional installs beyond pip"],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:01:41.358Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"abogen generates audiobooks with synchronized captions from ebooks in multiple languages using speech synthesis technologies, suitable for content creators who need to add auditory experiences to text-based media."}]}}