{"id":49770815,"url":"https://github.com/idvoretskyi/voice-transcriber","last_synced_at":"2026-05-11T12:50:53.881Z","repository":{"id":304235647,"uuid":"1018180356","full_name":"idvoretskyi/voice-transcriber","owner":"idvoretskyi","description":"Single-binary Ukrainian media-to-text transcription powered by Google Gemini via Vertex AI","archived":false,"fork":false,"pushed_at":"2026-04-14T20:08:34.000Z","size":15230,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-14T20:23:36.218Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://github.com/idvoretskyi/ukrainian-voice-transcriber","language":"Go","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/idvoretskyi.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":"SECURITY.md","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":"2025-07-11T18:43:36.000Z","updated_at":"2026-04-14T17:54:59.000Z","dependencies_parsed_at":"2025-08-02T18:35:13.845Z","dependency_job_id":"6d8b87a9-c1f5-4efc-a225-f8e489edcfdd","html_url":"https://github.com/idvoretskyi/voice-transcriber","commit_stats":null,"previous_names":["idvoretskyi/ukrainian-voice-transcriber","idvoretskyi/voice-transcriber"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/idvoretskyi/voice-transcriber","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idvoretskyi%2Fvoice-transcriber","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idvoretskyi%2Fvoice-transcriber/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idvoretskyi%2Fvoice-transcriber/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idvoretskyi%2Fvoice-transcriber/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/idvoretskyi","download_url":"https://codeload.github.com/idvoretskyi/voice-transcriber/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idvoretskyi%2Fvoice-transcriber/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32895968,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-10T13:40:02.631Z","status":"online","status_checked_at":"2026-05-11T02:00:05.975Z","response_time":120,"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":"2026-05-11T12:50:53.150Z","updated_at":"2026-05-11T12:50:53.873Z","avatar_url":"https://github.com/idvoretskyi.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Voice Transcriber\n\nSingle-binary media-to-text transcription with automatic language detection, powered by Google Gemini via Vertex AI.\n\n[![CI](https://github.com/idvoretskyi/voice-transcriber/actions/workflows/ci.yml/badge.svg)](https://github.com/idvoretskyi/voice-transcriber/actions/workflows/ci.yml)\n[![CodeQL](https://github.com/idvoretskyi/voice-transcriber/actions/workflows/codeql.yml/badge.svg)](https://github.com/idvoretskyi/voice-transcriber/actions/workflows/codeql.yml)\n[![Security](https://github.com/idvoretskyi/voice-transcriber/actions/workflows/security.yml/badge.svg)](https://github.com/idvoretskyi/voice-transcriber/actions/workflows/security.yml)\n[![Go version](https://img.shields.io/badge/go-1.25-00ADD8?logo=go)](https://go.dev/dl/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\n## Features\n\n- **Automatic language detection** — Gemini identifies the spoken language from audio (default)\n- Specify language explicitly with `--language` using an ISO 639-1 code (e.g. `uk`, `en`, `de`)\n- Accepts **audio and video files** as input\n- **No Cloud Storage required** — audio bytes sent inline to Gemini\n- FFmpeg used only for video-to-audio extraction; audio files go straight to Gemini\n- Handles files up to ~8.4 hours in a single request (no chunking)\n- Selectable Gemini model via `--model` flag (default: `gemini-3.1-flash-lite-preview`)\n- Single static binary — no extra runtime dependencies beyond FFmpeg for video\n\n## Quick Start\n\n### Prerequisites\n\n```bash\n# Go 1.25+\nbrew install go            # macOS\n# sudo apt install golang-go  # Ubuntu/Debian\n\n# FFmpeg (only required for video files)\nbrew install ffmpeg        # macOS\n# sudo apt install ffmpeg    # Ubuntu/Debian\n```\n\n### Install\n\n```bash\ngo install github.com/idvoretskyi/voice-transcriber/cmd/voice-transcriber@latest\n```\n\nThis installs the `voice-transcriber` binary into `$(go env GOPATH)/bin`.\n\n```bash\nexport PATH=\"$(go env GOPATH)/bin:$PATH\"\n```\n\n### Google Cloud setup\n\n```bash\n# Authenticate\ngcloud auth login\ngcloud auth application-default login\n\n# Set project and enable Vertex AI\ngcloud config set project YOUR_PROJECT_ID\ngcloud services enable aiplatform.googleapis.com\n```\n\nThe project is also read from the `GOOGLE_CLOUD_PROJECT` environment variable if set.\n\n### Usage\n\n```bash\n# Transcribe a video file (language auto-detected, audio extracted via FFmpeg)\nvoice-transcriber transcribe input/meeting.mp4\n\n# Transcribe an audio file directly\nvoice-transcriber transcribe input/interview.mp3\n\n# Specify output file\nvoice-transcriber transcribe input/meeting.mp4 -o transcript.txt\n\n# Force a specific language (ISO 639-1 code)\nvoice-transcriber transcribe input/meeting.mp4 --language uk\n\n# Use a different model or location\nvoice-transcriber transcribe input/meeting.mp4 --model gemini-3-flash-preview\nvoice-transcriber transcribe input/meeting.mp4 --model gemini-2.5-flash --location us-central1\n\n# Show version\nvoice-transcriber version\n```\n\n## CLI Reference\n\n```\nUsage:\n  voice-transcriber transcribe [media-file] [flags]\n  voice-transcriber version\n\nFlags:\n  --language string   Language for transcription: 'auto' for automatic detection,\n                      or ISO 639-1 code (e.g. uk, en, de) (default: auto)\n  --model string      Gemini model to use\n                      (default: gemini-3.1-flash-lite-preview)\n  --location string   Vertex AI location; Gemini 3.x models require global\n                      (default: global)\n  -o, --output string Output file path\n                      (default: output/\u003cname\u003e/\u003cname\u003e.txt)\n  -v, --verbose       Enable verbose output\n  -q, --quiet         Suppress all output except results\n```\n\n## Supported Formats\n\n| Type | Extensions |\n|------|------------|\n| **Audio** — sent directly to Gemini | `.wav` `.mp3` `.flac` `.ogg` `.m4a` `.aac` `.webm` `.pcm` |\n| **Video** — audio extracted via FFmpeg | `.mp4` `.mkv` `.mov` `.avi` `.wmv` `.flv` `.ts` `.mpeg` `.3gp` |\n\nExtension matching is case-insensitive. Maximum file size: 10 GB.\n\n## Building from Source\n\n```bash\ngit clone https://github.com/idvoretskyi/voice-transcriber.git\ncd voice-transcriber\nmake build   # produces ./voice-transcriber\nmake test    # run tests with race detector\nmake lint    # run golangci-lint\n```\n\n## License\n\nMIT — see [LICENSE](LICENSE) for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidvoretskyi%2Fvoice-transcriber","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fidvoretskyi%2Fvoice-transcriber","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidvoretskyi%2Fvoice-transcriber/lists"}