{"id":15136537,"url":"https://github.com/nikorasu/livewhisper","last_synced_at":"2025-04-06T14:13:04.119Z","repository":{"id":142250990,"uuid":"546926571","full_name":"Nikorasu/LiveWhisper","owner":"Nikorasu","description":"A nearly-live implementation of OpenAI's Whisper, using sounddevice. Requires existing Whisper install.","archived":false,"fork":false,"pushed_at":"2023-12-28T20:41:58.000Z","size":56,"stargazers_count":347,"open_issues_count":7,"forks_count":47,"subscribers_count":9,"default_branch":"main","last_synced_at":"2025-03-30T12:09:56.415Z","etag":null,"topics":["ai","assistant","chatbot","dictation","numpy","openai","openai-whisper","python","sounddevice","speech-recognition","speech-to-text","terminal","text-to-speech","transcription","translation","tts","voice","voice-assistant","voice-recognition","whisper"],"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/Nikorasu.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":"2022-10-06T21:57:33.000Z","updated_at":"2025-03-25T16:49:15.000Z","dependencies_parsed_at":"2024-01-14T14:39:30.652Z","dependency_job_id":"3b2a2bd2-0e48-42f2-98e7-cb53e7e676c6","html_url":"https://github.com/Nikorasu/LiveWhisper","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nikorasu%2FLiveWhisper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nikorasu%2FLiveWhisper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nikorasu%2FLiveWhisper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nikorasu%2FLiveWhisper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Nikorasu","download_url":"https://codeload.github.com/Nikorasu/LiveWhisper/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247492566,"owners_count":20947545,"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","assistant","chatbot","dictation","numpy","openai","openai-whisper","python","sounddevice","speech-recognition","speech-to-text","terminal","text-to-speech","transcription","translation","tts","voice","voice-assistant","voice-recognition","whisper"],"created_at":"2024-09-26T06:22:40.250Z","updated_at":"2025-04-06T14:13:04.098Z","avatar_url":"https://github.com/Nikorasu.png","language":"Python","funding_links":["https://ko-fi.com/nik85)!","https://ko-fi.com/F1F4GRRWB"],"categories":[],"sub_categories":[],"readme":"# LiveWhisper - Whisper based transcription\n\n`livewhisper.py` outputs psuedo-live sentence-by-sentence dictation to terminal.\nUsing [OpenAI's Whisper](https://github.com/openai/whisper) model, and sounddevice library to listen to microphone.\nAudio from mic is stored if it hits a volume \u0026 frequency threshold, then when\nsilence is detected, it saves the audio to a temp file and sends it to Whisper.\n\n*Dependencies:* Whisper, numpy, scipy, sounddevice\n\nLiveWhisper can somewhat work as an alternative to [SpeechRecognition](https://github.com/Uberi/speech_recognition).\nAlthough that now has it's own Whisper support, so it's up to you. ;)\n\n---\n\n## Whisper Assistant\n\nI've also included `assistant.py`, which using livewhisper as a base, is my\nattempt at making a simple voice-command assistant like Siri, Alexa, or Jarvis.\n\nSame dependencies as livewhisper, as well as requests, pyttsx3, wikipedia, bs4.\n*Also needs:* espeak and python3-espeak.\n\nThe voice assistant can be activated by saying it's name, default \"computer\",\n\"hey computer\" or \"okay computer\" also work. You can wait for the computer to\nthen respond, or immediately request an action/question without pausing.\n\nAvailable features: Weather, date \u0026 time, tell jokes, \u0026 do wikipedia searches.\nIt can also handle some other requests, like basic math or real simple trivia.\nTho that relies on Google's instant-answer snippets \u0026 sometimes doesn't work.\n\nControl media-players using: play, pause, next, previous, stop, what's playing?\nMedia controls need some form of noise/echo cancelling enabled to work right.\nSee [this page](https://www.linuxuprising.com/2020/09/how-to-enable-echo-noise-cancellation.html) for more information on how to enable that in Linux PulseAudio.\n\nYou can close the assistant via `ctrl+c`, or by saying it's name \u0026 \"terminate\".\n\n---\n\nIf you like my projects and want to help me keep making more,\nplease consider donating on [my Ko-fi page](https://ko-fi.com/nik85)! Thanks!\n\n[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/F1F4GRRWB)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnikorasu%2Flivewhisper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnikorasu%2Flivewhisper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnikorasu%2Flivewhisper/lists"}