{"id":51776459,"url":"https://github.com/42atomys/voxlevel","last_synced_at":"2026-07-20T06:30:37.840Z","repository":{"id":369894954,"uuid":"1205876635","full_name":"42atomys/voxlevel","owner":"42atomys","description":"normalize volume level to -6dB by DC removal, VAD and AGC","archived":false,"fork":false,"pushed_at":"2026-04-09T11:56:20.000Z","size":160,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-07T11:32:29.435Z","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/42atomys.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":"2026-04-09T11:16:10.000Z","updated_at":"2026-05-21T14:19:32.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/42atomys/voxlevel","commit_stats":null,"previous_names":["42atomys/voxlevel"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/42atomys/voxlevel","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/42atomys%2Fvoxlevel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/42atomys%2Fvoxlevel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/42atomys%2Fvoxlevel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/42atomys%2Fvoxlevel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/42atomys","download_url":"https://codeload.github.com/42atomys/voxlevel/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/42atomys%2Fvoxlevel/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35676362,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"ssl_error","status_checked_at":"2026-07-20T02:08:09.736Z","response_time":111,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":"2026-07-20T06:30:36.084Z","updated_at":"2026-07-20T06:30:37.835Z","avatar_url":"https://github.com/42atomys.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# voxlevel\n\nNormalize WAV voice recordings so all speakers sound at the same volume level (-6 dB by default), regardless of their distance from the microphone.\n\nHandles real-world scenarios: background noise, wind, echo, multiple speakers, and speakers moving during recording.\n\n## Installation\n\n```bash\npip install voxlevel\n```\n\n## Usage\n\n### Python API\n\n```python\nimport voxlevel\n\n# From a WAV file\nvoxlevel.normalize(\"input.wav\", \"output.wav\")\n\n# From a numpy array\nimport numpy as np\nresult = voxlevel.normalize(audio_array, sample_rate=16000)\n\n# With custom parameters\nvoxlevel.normalize(\n    \"input.wav\",\n    \"output.wav\",\n    target_db=-6.0,\n    max_gain_db=30.0,\n    rms_window_ms=400.0,\n    smooth_window_ms=200.0,\n)\n```\n\n### CLI\n\n```bash\n# Single file\nvoxlevel input.wav -o output.wav\n\n# Batch processing\nvoxlevel *.wav -o normalized/\n\n# Custom target level\nvoxlevel input.wav -o output.wav --target-db -3.0\n```\n\n## How it works\n\nvoxlevel uses a two-pass offline approach (not real-time compression):\n\n1. **Preprocessing** -- DC removal + 80 Hz high-pass filter to cut wind noise, handling noise, and plosives\n2. **Voice Activity Detection** -- Silero-VAD (ONNX) identifies speech vs. silence segments\n3. **Automatic Gain Control** -- Sliding RMS envelope computes the gain needed at each sample to reach the target level, with interpolation across silence gaps and bidirectional smoothing\n4. **Lookahead limiter** -- 5 ms lookahead prevents peaks from exceeding the target, reducing transient distortion compared to brick-wall clipping\n\nThe two-pass design means gain is correct from sample 0 -- no lag or adaptation artifacts that real-time compressors exhibit.\n\n## Constraints\n\n- 16-bit mono WAV at 8 kHz or 16 kHz\n- Offline processing only (no streaming)\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F42atomys%2Fvoxlevel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F42atomys%2Fvoxlevel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F42atomys%2Fvoxlevel/lists"}