{"id":51341604,"url":"https://github.com/sinhaankur/voice-harvester","last_synced_at":"2026-07-02T08:04:34.441Z","repository":{"id":366014629,"uuid":"1274740893","full_name":"sinhaankur/voice-harvester","owner":"sinhaankur","description":"Extract a clean, isolated voice from any video/audio file — ready for AI voice cloning (XTTS, RVC, ElevenLabs). Drag-and-drop app + CLI.","archived":false,"fork":false,"pushed_at":"2026-06-19T21:08:21.000Z","size":10,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-19T23:06:56.004Z","etag":null,"topics":["ai","audio","demucs","desktop-app","elevenlabs","ffmpeg","python","rvc","speech","tts","voice-cloning","voice-extraction","xtts"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sinhaankur.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-19T20:58:22.000Z","updated_at":"2026-06-19T21:08:25.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/sinhaankur/voice-harvester","commit_stats":null,"previous_names":["sinhaankur/voice-harvester"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/sinhaankur/voice-harvester","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sinhaankur%2Fvoice-harvester","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sinhaankur%2Fvoice-harvester/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sinhaankur%2Fvoice-harvester/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sinhaankur%2Fvoice-harvester/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sinhaankur","download_url":"https://codeload.github.com/sinhaankur/voice-harvester/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sinhaankur%2Fvoice-harvester/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35038266,"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":"2026-07-02T02:00:06.368Z","response_time":173,"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":["ai","audio","demucs","desktop-app","elevenlabs","ffmpeg","python","rvc","speech","tts","voice-cloning","voice-extraction","xtts"],"created_at":"2026-07-02T08:04:33.709Z","updated_at":"2026-07-02T08:04:34.434Z","avatar_url":"https://github.com/sinhaankur.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VoiceHarvester\n\nA small drag-and-drop desktop app that pulls a clean, isolated **voice** out of\nyour video and audio files and saves it as a WAV that's ready to feed into AI\nvoice-cloning tools (ElevenLabs, Play.ht, RVC, XTTS, and similar).\n\nDrop in as many files as you like — it processes them in a batch and can even\nstitch them into one combined sample for better cloning results.\n\n---\n\n## What it does\n\nFor each file it:\n\n1. Extracts the audio track.\n2. Isolates the spoken voice — using **Demucs** (deep-learning separation) if you\n   install it, otherwise an **ffmpeg** denoise/clean-up chain that always works.\n3. Cleans and normalizes the result to a **mono 44.1 kHz 16-bit WAV**, the format\n   cloning services prefer.\n\nOutput files are named `\u003coriginal\u003e_voice.wav`. With the merge option on, you also\nget `combined_voice_sample.wav`.\n\n---\n\n## Requirements\n\n**ffmpeg** must be installed (the app uses it under the hood):\n\n- macOS: `brew install ffmpeg`\n- Windows: `winget install Gyan.FFmpeg`\n- Linux: `sudo apt install ffmpeg`\n\n**Python 3.9+**, then optionally install the extras:\n\n```bash\npip install -r requirements.txt\n```\n\n- `tkinterdnd2` enables drag-and-drop. Without it, the app still works via the\n  **Add files...** button.\n- `demucs` (commented out in requirements) gives the best voice isolation but is\n  a large download. Enable it by uncommenting the line and re-running pip.\n\n---\n\n## Run it\n\n```bash\npython app.py\n```\n\nThen drag files onto the window (or click **Add files...**), pick an output\nfolder, and click **Extract Voice**.\n\n### Command-line version\n\nFor folders or automation, skip the GUI:\n\n```bash\npython cli.py /path/to/videos -o out/ --merge\n```\n\n---\n\n## Tips for good cloning results\n\n- Aim for **1–2+ minutes** of clear speech total. More clean audio = better clone.\n- Prefer clips with little background music or noise.\n- Use the **merge** option to combine several short clips into one sample.\n\n---\n\n## A note on consent\n\nCloning a real person's voice should be done with their consent, or — for a\nmemorial — in line with what your family is comfortable with. Reputable cloning\nservices require you to confirm you have the right to use the voice.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsinhaankur%2Fvoice-harvester","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsinhaankur%2Fvoice-harvester","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsinhaankur%2Fvoice-harvester/lists"}