{"id":26129462,"url":"https://github.com/ashwin-pc/whisper-dictation","last_synced_at":"2025-04-13T18:42:23.478Z","repository":{"id":279867567,"uuid":"940264052","full_name":"ashwin-pc/whisper-dictation","owner":"ashwin-pc","description":"A macOS application that converts speech to text using OpenAI's Whisper model running locally. Press the Globe/Function key to start recording, press it again to stop recording, transcribe, and paste text at your current cursor position.","archived":false,"fork":false,"pushed_at":"2025-03-10T03:21:58.000Z","size":14,"stargazers_count":4,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T09:23:34.944Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ashwin-pc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-02-27T22:03:45.000Z","updated_at":"2025-03-23T14:46:54.000Z","dependencies_parsed_at":null,"dependency_job_id":"56d720d1-100e-40c7-9217-3aba972bb302","html_url":"https://github.com/ashwin-pc/whisper-dictation","commit_stats":null,"previous_names":["ashwin-pc/whisper-dictation"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwin-pc%2Fwhisper-dictation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwin-pc%2Fwhisper-dictation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwin-pc%2Fwhisper-dictation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwin-pc%2Fwhisper-dictation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ashwin-pc","download_url":"https://codeload.github.com/ashwin-pc/whisper-dictation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248764732,"owners_count":21158145,"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":"2025-03-10T19:48:52.322Z","updated_at":"2025-04-13T18:42:23.449Z","avatar_url":"https://github.com/ashwin-pc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Whisper Dictation\n\n**Note: This application is for macOS only.**\n\nA macOS application that converts speech to text using OpenAI's Whisper model running locally. Press the Globe/Function key to start recording, press it again to stop recording, transcribe, and paste text at your current cursor position.\n\n## Features\n\n- System tray (menu bar) application that runs in the background\n- Global hotkey (Globe/Function key) to trigger dictation\n- Transcribes speech to text using OpenAI's Whisper model locally\n- Automatically pastes transcribed text at your cursor position\n- Visual feedback with menu bar icon status\n\n## Setup and Installation\n\n### Development Setup\n\n1. Install Python dependencies:\n```\npip install -r requirements.txt\n```\n\n2. Install PortAudio (required for PyAudio):\n```\nbrew install portaudio\n```\n\n3. Run the application in development mode:\n```\npython src/main.py\n```\n\n### Running the Script in the Background\n\nTo run the script in the background:\n\n1. Install all dependencies:\n```\npip install -r requirements.txt\n```\n\n2. Run the script in the background:\n```\nnohup ./run.sh \u003e/dev/null 2\u003e\u00261 \u0026 disown\n```\n\n3. The script will continue running in the background. You can then use the app as described in the Usage section.\n\n## Usage\n\n1. Launch the Whisper Dictation app. You'll see a microphone icon (🎙️) in your menu bar.\n2. Press the Globe key or Function key on your keyboard to start recording.\n3. Speak clearly into your microphone.\n4. Press the Globe/Function key again to stop recording.\n5. The app will transcribe your speech and automatically paste it at your current cursor position.\n\nYou can also interact with the app through the menu bar icon:\n- Click \"Start/Stop Listening\" to toggle recording\n- Access Settings for configuration options\n- Click \"Quit\" to exit the application\n\n## Permissions\n\nThe app requires the following permissions:\n- Microphone access (to record your speech).  \n  Go to System Preferences → Security \u0026 Privacy → Privacy → Microphone and add your Terminal or the app.\n- Accessibility access (to simulate keyboard presses for pasting).  \n  Go to System Preferences → Security \u0026 Privacy → Privacy → Accessibility and add your Terminal or the app.\n\n## Requirements\n\n- macOS 10.14 or later\n- Microphone\n\n## Troubleshooting\n\nIf something goes wrong or you need to stop the background process, you can kill it by running one of the following commands in your Terminal:\n\n1. List the running process(es):\n```\nps aux | grep 'src/main.py'\n```\n2. Kill the process by its PID:\n```\nkill -9 \u003cPID\u003e\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashwin-pc%2Fwhisper-dictation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fashwin-pc%2Fwhisper-dictation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashwin-pc%2Fwhisper-dictation/lists"}