{"id":24617692,"url":"https://github.com/jacoblincool/whisper-cli","last_synced_at":"2025-05-07T05:24:47.490Z","repository":{"id":115752473,"uuid":"610000187","full_name":"JacobLinCool/whisper-cli","owner":"JacobLinCool","description":"A CLI speech recognition tool, using OpenAI Whisper, supports audio file transcription and near-realtime microphone input.","archived":false,"fork":false,"pushed_at":"2025-05-07T00:19:21.000Z","size":382,"stargazers_count":16,"open_issues_count":13,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-07T01:27:24.442Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","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/JacobLinCool.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,"zenodo":null}},"created_at":"2023-03-05T21:14:06.000Z","updated_at":"2025-04-09T10:24:24.000Z","dependencies_parsed_at":"2024-07-05T19:01:02.627Z","dependency_job_id":"08775922-87bc-4aa4-9e13-2c93ac3eae7a","html_url":"https://github.com/JacobLinCool/whisper-cli","commit_stats":null,"previous_names":[],"tags_count":9,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JacobLinCool%2Fwhisper-cli","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JacobLinCool%2Fwhisper-cli/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JacobLinCool%2Fwhisper-cli/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JacobLinCool%2Fwhisper-cli/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JacobLinCool","download_url":"https://codeload.github.com/JacobLinCool/whisper-cli/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252819620,"owners_count":21809052,"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":"2025-01-24T23:39:57.615Z","updated_at":"2025-05-07T05:24:47.471Z","avatar_url":"https://github.com/JacobLinCool.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Whisper CLI\n\nA CLI speech recognition tool, using OpenAI Whisper, supports audio file transcription and near-realtime microphone input.\n\nIt supports running [Smart Whisper](https://github.com/JacobLinCool/smart-whisper) locally with `whisper smart` subcommand.\n\n```sh\n❯ whisper help\nUsage: whisper [options] [command]\n\nA CLI speech recognition tool, using OpenAI Whisper, supports audio file transcription and near-realtime microphone input.\n\nOptions:\n  -V, --version                            output the version number\n  -h, --help                               display help for command\n\nCommands:\n  recognize|rec [options] \u003caudio\u003e          Recognize text from an audio file\n  microphone|mic [options]                 Recognize text from microphone\n  help [command]                           display help for command\n```\n\n## Installation\n\n```sh\nnpm install -g whisper-cli\n```\n\n## Usage\n\nYou need to set the `OPENAI_API_KEY` environment variable first.\n\n\u003e You can also put it in a `.env` file in the current directory.\n\n```sh\nwhisper help\n```\n\n### Smart Whisper\n\n[Smart Whisper](https://github.com/JacobLinCool/smart-whisper) allows you to run whisper locally with native performance.\n\n```sh\nwhisper smart help # show help\nwhisper smart model download base # download base model\nwhisper smart transcribe \u003caudio\u003e --gpu --model base # transcribe audio file with base model on GPU\nwhisper smart server --gpu --port 3000 --model large-v3 # run server on port 3000 with large-v3 model on GPU\n```\n\n`whisper smart server` runs a transcribe server, which manages the model memory automatically, it will offload the model when idling, and load it back when needed.\n\nThe OpenAPI spec is available at `http://localhost:\u003cport\u003e/openapi.json`. You can use API-Spec to browse it: \u003chttps://api-spec.pages.dev/rapidoc?url=http%3A%2F%2Flocalhost%3A3000%2Fopenapi.json\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacoblincool%2Fwhisper-cli","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjacoblincool%2Fwhisper-cli","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacoblincool%2Fwhisper-cli/lists"}