Skip to content
Back to search

DayBee

Desktop microphone recorder with real-time, on-device transcription, automatic audio segmentation, voice activity detection, and an MCP server for searching saved transcripts.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nexmoe--daybee/badge.svg)](/listings/nexmoe--daybee)

HTML

<a href="/listings/nexmoe--daybee"><img src="/api/listings/nexmoe--daybee/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 71 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # DayBee
  2. English | [中文](README.zh.md)
  3. DayBee is a tray-first desktop recorder built with Go and mygo. It records microphone audio for long sessions, segments files automatically, and uses Apple SpeechAnalyzer or selectable `sherpa-onnx` ASR models plus Silero VAD for live transcription and offline reprocessing.
  4. ## Features
  5. - Long-running microphone recording with automatic segmentation
  6. - Live transcription with Apple SpeechAnalyzer, lightweight Whisper Tiny/Base/Small, SenseVoice Small, Qwen3 ASR 0.6B or FireRedASR2 AED/CTC (can be disabled)
  7. - VAD-only recording — only speech segments are saved to disk
  8. - Real-time waveform visualization
  9. - Manual microphone selection with automatic switch to the more active input
  10. - Native echo cancellation on macOS to reduce speaker playback in recordings and transcripts
  11. - Optional macOS system audio capture, saved and displayed separately from microphone speech
  12. - Automatic recording on launch and lossless FLAC archives
  13. - Batch transcription of existing WAV/FLAC recordings
  14. - Timeline of complete saved transcripts
  15. - Built-in MCP server for listing, searching and reading saved transcripts from AI assistants; copy the client configuration from General settings. See [MCP setup and tools](docs/subsystem/mcp.md).
  16. - Annotate transcripts with app names and icons from the same recording period
  17. - System tray app with launch-at-login, start-on-launch, and auto-update
  18. - Bilingual UI (English / 中文)
  19. - Light / Dark / System theme
  20. ## Desktop Preview
  21. ![DayBee desktop app](docs/images/desktop-gui-preview.png)
  22. ## Download
  23. - Release page: [DayBee Releases](https://github.com/nexmoe/DayBee/releases)
  24. - macOS 13.3+: Apple Silicon / Intel `.dmg`
  25. - Windows: `.exe` (NSIS installer)
  26. The packaged app checks for signed updates on startup and every six hours, then installs and restarts when recording and transcription are idle. The first upgrade from Electron requires a manual installation; see the [migration verification and upgrade notes](docs/migration-verification.md). Releases require automated checks on all three platforms; outstanding manual migration acceptance remains recorded in the verification report.
  27. ## Runtime Notes
  28. - Compatible Macs running macOS 26 or later default to Apple SpeechAnalyzer for on-device transcription. Older Macs and other platforms default to Whisper Tiny (INT8). Existing model choices are preserved; all models remain selectable in Transcribe settings. SpeechAnalyzer resources are managed by macOS, and its System language option follows your Mac's preferred languages; select a language for other audio. Models can be switched while recording, and queued speech retains its original model and language. See [speech recognition](docs/subsystem/asr.md).
  29. - Silero VAD downloads when recording starts. The selected ASR model downloads when chosen or when live/batch transcription first needs it. Existing model caches are reused; failed downloads preserve the previous selection.
  30. - Native audio capture, sherpa-onnx 1.13.8 and ONNX Runtime 1.28.2 are bundled. Installed apps need no Node.js, Bun or Go runtime.
  31. - WAV/FLAC encoding, decoding, downmixing and resampling run directly in Go. Existing FLAC recordings remain readable; no FFmpeg executable or system installation is required.
  32. - On macOS, echo cancellation is enabled by default, including for existing settings. Turn it off in Input for unprocessed capture. Auto-switch input remains independently configurable and keeps echo cancellation enabled after switching; disconnect recovery remains available. See [echo cancellation](docs/subsystem/audio.md). System audio recording is opt-in on the same page; see [source separation](docs/subsystem/audio.md).
  33. - Microphone app detection runs independently while DayBee is open, checks once per second, and requires macOS 14.2+ on Mac. Daily archives are stored under `microphone-activity/` in the app data directory. See [microphone activity notes](docs/subsystem/microphone-activity.md).
  34. ## Output
  35. - Audio and transcript JSON files are archived under `recordings/YYYYMMDD/`
  36. - Filenames look like `daybee_YYYYMMDD_HHMMSS.wav` or `.flac`
  37. - With ASR enabled, each segment writes a matching `.json` with transcript text and metadata. ASR-disabled recording saves audio and capture timing metadata without transcript text.
  38. Example JSON:
  39. ```json
  40. {
  41. "audio_file": "daybee_20260201_120513.wav",
  42. "audio_path": "/path/to/recordings/20260201/daybee_20260201_120513.wav",
  43. "backend": "sherpa-onnx",
  44. "created_at": "2026-02-01T12:05:13.000Z",
  45. "input_device": "MacBook Air Microphone",
  46. "model": "Qwen3 ASR 0.6B",
  47. "segment_start_time": "2026-02-01T12:05:13.000Z",
  48. "status": "ok",
  49. "text": "Please stand up and stretch for a minute."
  50. }
  51. ```
  52. ## More Documentation
  53. - [Subsystem reference](docs/subsystem/README.md)
  54. - [Changelog](CHANGELOG.md)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.