{"id":15055275,"url":"https://github.com/drewthomasson/doc2interview","last_synced_at":"2026-03-03T07:31:53.656Z","repository":{"id":254537500,"uuid":"846845720","full_name":"DrewThomasson/doc2interview","owner":"DrewThomasson","description":"This is an interface that will offline convert anything pdf document you give it into an interview between two people discussing it.","archived":false,"fork":false,"pushed_at":"2024-12-08T04:06:01.000Z","size":606,"stargazers_count":13,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-30T19:50:28.258Z","etag":null,"topics":["generative-ai","ollama","pdf","tts","xtts"],"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/DrewThomasson.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}},"created_at":"2024-08-24T05:39:36.000Z","updated_at":"2025-03-22T18:10:58.000Z","dependencies_parsed_at":"2024-11-19T19:46:12.297Z","dependency_job_id":"7decf5be-e48c-4f24-979a-c3ae64931bf4","html_url":"https://github.com/DrewThomasson/doc2interview","commit_stats":{"total_commits":19,"total_committers":1,"mean_commits":19.0,"dds":0.0,"last_synced_commit":"2d90b381dc8a1bda24525d6ef71332739efc33b6"},"previous_names":["drewthomasson/doc2interview"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DrewThomasson/doc2interview","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrewThomasson%2Fdoc2interview","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrewThomasson%2Fdoc2interview/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrewThomasson%2Fdoc2interview/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrewThomasson%2Fdoc2interview/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DrewThomasson","download_url":"https://codeload.github.com/DrewThomasson/doc2interview/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrewThomasson%2Fdoc2interview/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271061443,"owners_count":24692535,"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","status":"online","status_checked_at":"2025-08-18T02:00:08.743Z","response_time":89,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["generative-ai","ollama","pdf","tts","xtts"],"created_at":"2024-09-24T21:39:55.544Z","updated_at":"2026-03-03T07:31:53.626Z","avatar_url":"https://github.com/DrewThomasson.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎙️ doc2interview\n\nWelcome to the Interview Audio Generator! \nThis  innovative tool automatically transforms PDF documents or online articles into engaging interview-style audio files. \nIt's perfect for auditory learners or anyone who enjoys consuming content on the go!\nAnd best of all it runs entirly locally on your computer! No paid api services or anything.\n\n## 📋 Prerequisites\n\nEnsure you have the following installed:\n- Python 3.8+\n- Ollama with the `phi3.5` model pulled\n\n- For faster results have a cuda capable machine so xtts can generate faster with a minimum of 4gb Vram\n\n\n## 🛠️ Installation\n\n1. **Clone the repository**:\n   ```bash\n   git clone https://github.com/DrewThomasson/doc2interview.git\n   cd doc2interview\n   ```\n\n2. **Install required Python packages**:\n   - Install all necessary Python packages using the following command:\n     ```bash\n     pip install -r requirements.txt\n     ```\n\n3. **Setup Ollama**:\n   - Install Ollama following the official documentation. [link here](https://ollama.com)\n   - Pull the `phi3.5` model necessary for running the script:\n     ```bash\n     ollama pull phi3.5\n     ```\n\n## 🚀 Quick Start\n\n1. **Start the script**:\n   ```bash\n   python summarize_local.py\n   ```\n2. **Open the Gradio interface**:\n   - The interface will be available in your web browser.\n   - Upload a PDF or enter an article URL.\n   - Choose the language and let the magic happen!\n\n## 📁 Output\n\nThe generated audio files will be stored in:\n- **Chapter-wise audio**: `./output_audio/`\n- **Final combined audio**: `./final_output_audio_dir/final_output_audio.wav`\n\nFeel free to explore the audio files and use them as needed!\n\n## 🎧 Demo\n\nCheck out this sample audio from a generated interview:\n\nhttps://github.com/user-attachments/assets/77e6046d-18e0-41dd-b034-7cdd709b9daf\n\n[Generated from this article](https://www.chosun.com/english/industry-en/2024/08/21/GGIYIGY43VHHVA2J74VAVWLEDQ/)\n\n\n## To-Do List\n\n- [ ] **Attempt to find a way to remove any ramlbings at the end.**  \n  For more details, see the issue request [here](https://github.com/DrewThomasson/doc2interview/issues/2#issue-2501722522).\n\n- [ ] **Allow users to easily swap the ref audio for either voice actors in gui.**\n\n- [ ] **Find a way for the program to be able to determine which speakers in generated dialog are male or female.**  \n  Possably by just asking the llm.\n\n- [ ] **Allow user to see streaming llm outout**  \n  Right now you cant see the llm working live in the terminal, and only see the llm output once its finished writing the dialog script.\n\n- [ ] **Have program automatically run the ollama pull command if the specified model isnt found?**  \n  Not that huge of an issue though.\n\n- [ ] **Have a bulk process mulitple files or documents feature**\n\n\n\n## 🤝 Contributing\n\nContributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are **greatly appreciated**.\n\n## 📖 License\n\nDistributed under the MIT License. See `LICENSE` for more information.\n\n## ❓ Support\n\nGot questions? Feel free to open an issue or contact me directly at your-email@example.com.\n\n## 🌟 Show your support\n\nGive a ⭐️ if this project helped you!\n\n## Inspired by \nAiPeterWorld with his non-offline version which used gemini flash and openai voice for tts\n\nhttps://huggingface.co/spaces/AIPeterWorld/Doc-To-Dialogue\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrewthomasson%2Fdoc2interview","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdrewthomasson%2Fdoc2interview","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrewthomasson%2Fdoc2interview/lists"}