{"id":50948682,"url":"https://github.com/oduerr/mywhisper","last_synced_at":"2026-06-17T23:03:21.436Z","repository":{"id":357788757,"uuid":"1238537953","full_name":"oduerr/mywhisper","owner":"oduerr","description":"Simple voice to text adpoted to my needs","archived":false,"fork":false,"pushed_at":"2026-05-14T10:26:50.000Z","size":98,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-14T10:31:50.428Z","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/oduerr.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-14T07:58:05.000Z","updated_at":"2026-05-14T10:26:54.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/oduerr/mywhisper","commit_stats":null,"previous_names":["oduerr/mywhisper"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/oduerr/mywhisper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oduerr%2Fmywhisper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oduerr%2Fmywhisper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oduerr%2Fmywhisper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oduerr%2Fmywhisper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oduerr","download_url":"https://codeload.github.com/oduerr/mywhisper/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oduerr%2Fmywhisper/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34468766,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-17T02:00:05.408Z","response_time":127,"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":[],"created_at":"2026-06-17T23:03:20.901Z","updated_at":"2026-06-17T23:03:21.431Z","avatar_url":"https://github.com/oduerr.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# mywhisper\n\nA lightweight voice-to-text tool using [mlx_whisper](https://github.com/ml-explore/mlx-examples/tree/main/whisper), tailored to my needs. Hold a hotkey, speak, and get the transcription pasted at the cursor position.\n\n## Setup\n\n```bash\nuv sync\nsource .venv/bin/activate\n```\n\n## Running the app\n\n```bash\npython mywhisper.py\n```\n\nA small floating window appears in the bottom-right corner. Hold **right ⌥ (Option)** to record, release to transcribe — the text is pasted at the cursor position in whatever app is focused.\n\nFirst launch downloads and warm-starts the model (~15s); subsequent launches are fast.\n\n### macOS permissions (required once)\n\nThe app needs two permissions:\n\n**1. Accessibility** — for the global hotkey and simulated paste (Cmd+V):\n\n- Open **System Settings → Privacy \u0026 Security → Accessibility**\n- Click **+** and add your terminal app (Terminal.app or iTerm2)\n- Restart the app\n\nWithout this you'll see `This process is not trusted!` and the hotkey won't work.\n\n**2. Microphone** — macOS will prompt automatically on first use.\n\n## openai_translate.py\n\nReal-time speech translator using the OpenAI Realtime Translate API (`gpt-realtime-translate`). Hold right ⌥, speak any language, release — the translation is spoken aloud, pasted at the cursor, and shown in the UI.\n\nThe input language is **auto-detected** by the API; only the output language is configured:\n\n```bash\npython openai_translate.py                 # → Chinese (default)\npython openai_translate.py --lang en       # → English\npython openai_translate.py --lang fr       # → French\npython openai_translate.py --help\n```\n\nRequires `OPENAI_API_KEY` to be set in your environment. Billed at $0.034/min of audio.\n\nSame macOS Accessibility permission as `mywhisper.py` applies here too.\n\n\u003e **Known limitation:** audio is sent to the API only after you release the key (batch mode), so latency scales with recording length. A proper fix would stream audio to the API while you're still speaking — that's a future improvement.\n\n`test_translate.py` is a minimal script for testing the pipeline with a WAV file without the UI:\u003c/p\u003e\n\n```bash\npython test_translate.py recordings/\u003cfolder\u003e/output.wav zh\n```\n\n## benchmark.py\n\nInternal script for evaluating mlx_whisper transcription quality against a set of reference recordings (from SuperWhisper). Not intended for general use — the `recordings/` directory is local-only and not checked in.\n\n```bash\npython benchmark.py                                        # default model\npython benchmark.py --model mlx-community/whisper-large-v3\n```\n\nGenerates `benchmark_report.html` with a side-by-side comparison of SuperWhisper and mlx_whisper transcripts, including inline audio playback.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foduerr%2Fmywhisper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foduerr%2Fmywhisper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foduerr%2Fmywhisper/lists"}