{"id":24583774,"url":"https://github.com/assemblyai-solutions/aai-csv-bulk-upload","last_synced_at":"2025-03-17T17:25:14.276Z","repository":{"id":197107869,"uuid":"697972428","full_name":"AssemblyAI-Solutions/aai-csv-bulk-upload","owner":"AssemblyAI-Solutions","description":null,"archived":false,"fork":false,"pushed_at":"2023-09-29T02:27:03.000Z","size":8,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-24T04:53:33.339Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/AssemblyAI-Solutions.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}},"created_at":"2023-09-28T21:29:22.000Z","updated_at":"2023-09-29T15:32:48.000Z","dependencies_parsed_at":"2023-09-29T02:10:03.201Z","dependency_job_id":null,"html_url":"https://github.com/AssemblyAI-Solutions/aai-csv-bulk-upload","commit_stats":null,"previous_names":["zkleb-aai/aai-csv-bulk-upload"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AssemblyAI-Solutions%2Faai-csv-bulk-upload","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AssemblyAI-Solutions%2Faai-csv-bulk-upload/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AssemblyAI-Solutions%2Faai-csv-bulk-upload/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AssemblyAI-Solutions%2Faai-csv-bulk-upload/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AssemblyAI-Solutions","download_url":"https://codeload.github.com/AssemblyAI-Solutions/aai-csv-bulk-upload/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244076055,"owners_count":20394048,"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":[],"created_at":"2025-01-24T04:53:41.397Z","updated_at":"2025-03-17T17:25:14.255Z","avatar_url":"https://github.com/AssemblyAI-Solutions.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AssemblyAI Transcript Downloader\n\n## [Video Walkthrough](https://www.veed.io/view/a562623d-b689-4e5c-81b6-5e9f77cf31ad?panel=share)\n\nThis repository contains a Python application that takes a CSV file with a list of audio/video URLs as input and retrieves the transcript of each audio/video URL, saving them as text files in a folder named `transcripts_txt_files`. It accomplishes this task by utilizing the AssemblyAI Transcript API.\n\n## Usage Instructions\n\nFollow these steps to use this application:\n\n1. **Clone the Repository:**\n\n`git clone https://github.com/zkleb-aai/aai-csv-bulk-upload.git`\n\n\n2. **Create a Python Virtual Environment:**\n\n`python3 -m venv venv`\n\n\n3. **Activate the Virtual Environment:**\n\nOn macOS/Linux: `source venv/bin/activate`\n\nOn Windows (Command Prompt): `venv\\Scripts\\activate`\n\n\n4. **Install Requirements:**\n\n`pip3 install -r requirements.txt`\n\n\n5. **Create an Ngrok Connection:**\n- Open a new terminal window.\n- Start an Ngrok connection on port 5002:\n  ```\n  ngrok http 5002\n  ```\n\n6. **Create a `.env` File:**\n- Create a file named `.env` in the project directory.\n- Add your AssemblyAI API key to the `.env` file as follows:\n  ```\n  AAI_KEY=enter_your_assemblyai_api_key\n  ```\n\n7. **Start the Flask App:**\n- Open another terminal window.\n- Start the Flask application:\n  ```\n  python3 main.py\n  ```\n\n8. **Execute the Bulk Upload:**\n- Put a CSV file containing the list of URLs for transcription in the project directory.\n- Open another terminal window.\n- Execute the bulk upload script:\n  ```\n  python3 bulk_upload.py\n  ```\n- You will be prompted to write the name of the CSV file.  Alternatively, you can also hardcode this CSV filename in [line 15 of the bulk_upload.py file](https://github.com/zkleb-aai/aai-csv-bulk-upload/blob/main/bulk_upload.py#L15).\n\n\n\n9. **Check the Logs:**\n- The Flask application logs will notify you of how many transcriptions have been received.\n- You can monitor the progress and completion of the transcription process in these logs.\n\n## Requirements\n\nMake sure you have the following installed:\n- Python 3.x\n- Pip3 (Python package manager)\n- [Ngrok](https://ngrok.com/) (for creating a public tunnel to your local Flask app)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fassemblyai-solutions%2Faai-csv-bulk-upload","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fassemblyai-solutions%2Faai-csv-bulk-upload","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fassemblyai-solutions%2Faai-csv-bulk-upload/lists"}