{"id":21713530,"url":"https://github.com/nitrictech/pycasts","last_synced_at":"2025-04-12T18:46:31.342Z","repository":{"id":264519343,"uuid":"872132708","full_name":"nitrictech/pycasts","owner":"nitrictech","description":"A text to Podcast inference API","archived":false,"fork":false,"pushed_at":"2024-11-11T23:05:27.000Z","size":2224,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-06T03:36:13.198Z","etag":null,"topics":["ai","llama","llm","machine-learning","nitric","python","torch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nitrictech.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":"nitrictech"}},"created_at":"2024-10-13T21:23:23.000Z","updated_at":"2025-03-11T15:46:08.000Z","dependencies_parsed_at":"2024-11-24T20:38:54.562Z","dependency_job_id":"606d8241-b5ed-4956-aa97-6d6bd8a4a37f","html_url":"https://github.com/nitrictech/pycasts","commit_stats":null,"previous_names":["nitrictech/pycasts"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nitrictech%2Fpycasts","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nitrictech%2Fpycasts/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nitrictech%2Fpycasts/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nitrictech%2Fpycasts/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nitrictech","download_url":"https://codeload.github.com/nitrictech/pycasts/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248617569,"owners_count":21134195,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","llama","llm","machine-learning","nitric","python","torch"],"created_at":"2024-11-26T00:17:21.197Z","updated_at":"2025-04-12T18:46:31.313Z","avatar_url":"https://github.com/nitrictech.png","language":"Python","funding_links":["https://github.com/sponsors/nitrictech"],"categories":[],"sub_categories":[],"readme":"## Pycasts\n\nPycasts is a reference API for producing long form spoken audio and scripts for podcasts, powered by [Nitric](https://github.com/nitrictech/nitric), [Suno Bark](https://huggingface.co/suno/bark) and [Llama 3.2](https://www.llama.com/).\n\nHere's a sample of what can be produced with this project:\n\n[power-rangers.webm](https://github.com/user-attachments/assets/bcb03055-c5d6-4883-8d0f-45fdf45191ca)\n\nIf you'd like a step-through guide on producing this API see [here](https://nitric.io/docs/guides/python/ai-podcast-part-1)\n\n## Running locally\n\nFirst off install project dependencies:\n\n```bash\nuv sync --all-extras\n```\n\nThis project uses also uses smaller LLMs for producing podcast scripts, which is baked directly into the resulting container when we deploy, via the `models` directory of the project.\n\nThis can be populated by downloading an appropriately sized and quantized Llama 3.2 model. As an example:\n\n```bash\nmkdir models\ncurl -L https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_L.gguf -o models/Llama-3.2-3B-Instruct-Q4_K_L.gguf\n```\n\nThe project can be then run locally by installing the [Nitric CLI](https://nitric.io/docs/get-started/installation). And running\n```bash\nnitric start\n```\n\nThis will start the project on your local machine, and you will be able to use the provided local [nitric dashboard](https://localhost:49152), or your HTTP client of choice to interact with the API.\n\nAudio models are downloaded ahead of time using the API to be stored locally in a bucket, this can be done by hitting the `/download-model` endpoint:\n\n```bash\ncurl -X POST http://localhost:4001/download-model\n```\n\u003e Assuming your API is hosted on 4001 (check your CLI output for `nitric start`).\n\nOnce the model has been fetched you're good to run the start generating podcasts.\n\nFor example\n\n```bash\ncurl -X POST http://localhost:4001/podcast/peanut \\\n     -H \"Content-Type: text/plain\" \\\n     -d \"A podcast about the history of the peanut\"\n```\n\nWould produce a short podcast style script and audio on the history of the peanut 🥜.\n\nWatch the logs in your CLI to see progress for now. Your output audio will be available in the `clips` bucket once everything has generated. See the local nitric dashboard [storage](http://localhost:49152/storage), to download your finished podcast.\n\n## Deploying this project\n\nA reference for deploying to AWS is provided along with the project under `nitric.aws.yaml`. \n\nFor info on pre-requisites and setup see the [Nitric AWS provider docs](https://nitric.io/docs/providers/pulumi/aws).\n\nYou can also consult this [guide](https://nitric.io/docs/guides/python/ai-podcast-part-1) for instructions specific to this project.\n\nNitric supports GCP for this app, and may be included as a reference for this project in future as well.\n\n## Possible project extensions\n\n- [ ] Remove API endpoints and make podcasts on a schedule\n- [ ] Use different voice models\n- [ ] Add support for multiple speakers\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnitrictech%2Fpycasts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnitrictech%2Fpycasts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnitrictech%2Fpycasts/lists"}