{"data":{"slug":"open-mmlab-amphion","name":"Amphion","tagline":"A toolkit for Audio, Music, and Speech Generation to support reproducible research","github_url":"https://github.com/open-mmlab/Amphion","owner":"open-mmlab","repo":"Amphion","owner_avatar_url":"https://avatars.githubusercontent.com/u/10245193?v=4","primary_language":"Python","stars":9973,"forks":830,"topics":["audio-generation","audio-synthesis","audioldm","audit","emilia","fastspeech2","maskgct","music-generation","naturalspeech2","singing-voice-conversion","speech-synthesis","text-to-audio","text-to-speech","vall-e","vits","vocoder","voice-conversion"],"archived":false,"github_pushed_at":"2026-03-25T14:11:57+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/open-mmlab-amphion","markdown_url":"https://www.graphcanon.com/tools/open-mmlab-amphion.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/open-mmlab-amphion","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=open-mmlab-amphion","description":"Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.","homepage_url":"https://openhlt.github.io/amphion/","license":"MIT","open_issues":175,"watchers":90,"ai_summary":"Amphion is a Python-based toolkit designed for junior researchers and engineers working in audio, music, and speech generation.","readme_excerpt":"## 📀 Installation\n\nAmphion can be installed through either Setup Installer or Docker Image.\n\n---\n\n# Install Python Environment\nconda create --name amphion python=3.9.15\nconda activate amphion\n\n---\n\n# Install Python Packages Dependencies\nsh env.sh\n```\n\n---\n\n### Docker Image\n\n1. Install [Docker](https://docs.docker.com/get-docker/), [NVIDIA Driver](https://www.nvidia.com/download/index.aspx), [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html), and [CUDA](https://developer.nvidia.com/cuda-downloads).\n\n2. Run the following commands:\n```bash\ngit clone https://github.com/open-mmlab/Amphion.git\ncd Amphion\n\ndocker pull realamphion/amphion\ndocker run --runtime=nvidia --gpus all -it -v .:/app realamphion/amphion\n```\nMount dataset by argument `-v` is necessary when using Docker. Please refer to [Mount dataset in Docker container](egs/datasets/docker.md) and [Docker Docs](https://docs.docker.com/engine/reference/commandline/container_run/#volume) for more details.\n\n---\n\n## ©️ License\n\nAmphion is under the [MIT License](LICENSE). It is free for both research and commercial use cases.","github_created_at":"2023-11-15T09:19:27+00:00","created_at":"2026-07-11T12:05:19.698735+00:00","updated_at":"2026-07-29T06:00:40.886769+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":"audio-generation","name":"audio-generation"},{"slug":"music-generation","name":"music-generation"},{"slug":"singing-voice-conversion","name":"singing-voice-conversion"},{"slug":"speech-synthesis","name":"speech-synthesis"},{"slug":"text-to-audio","name":"text-to-audio"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"vocoder","name":"vocoder"},{"slug":"voice-conversion","name":"voice-conversion"}],"trust":{"provenance":{"is_fork":false,"github_id":719017363,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-29T06:00:40.016Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":125,"last_release_at":"2024-02-23T17:52:41Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:05:23.883Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-29T06:00:40.469Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-29T06:00:40.469Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-29T06:00:40.469Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-29T06:00:40.469Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-29T06:00:40.469Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you are new to the field of audio, music, or speech generation and seeking a toolkit that simplifies setup with Python dependencies and Docker images.","If reproducible research is essential for your project; Amphion streamlines this through its well-defined installation methods."],"when_not_to_use":["If you require advanced customization beyond what the provided Python packages offer, since Amphion caters more to getting started quickly without deep configuration."],"source":"enrich:decision_facts","observed_at":"2026-07-16T23:03:20.431Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Amphion offers support for reproducible research in audio, music, and speech generation through Python dependencies and Docker images that junior researchers and engineers can readily use."}]}}