Documentation
Audio & transcription
SystemSculpt’s recorder and transcription services run entirely inside the plugin—no external scripts required.
Recording controls
Toggle the recorder with ⌘/Ctrl + R or the command palette. The toolbar appears inside Obsidian so you never leave the note you are working on.
- •The recorder remembers your preferred microphone, watches for device changes, and recovers if a track drops.
- •The recording modal gives you transport controls, a waveform preview, and live status messages.
- •Existing recordings upload through the SystemSculpt service so you can transcribe files you already captured.
Settings tie-ins
The Recording tab controls automatic transcription, clean output, and auto-submit. Changes apply the next time you open the recorder.
Transcription flow
When you submit audio, the plugin cleans the file, uploads it, monitors progress, and finalises the transcript.
- •Audio is normalised automatically (with optional resampling) before it uploads.
- •Progress updates stream back to the modal so you can see when a job starts, queues, and finishes.
- •Optional post-processing prompts run after the transcript completes when the toggle is enabled in settings.
Command paletteTranscribe with SystemSculpt uses the same pipeline as the recorder, just without capturing new audio.
DiagnosticsErrors appear as Obsidian notices and in the exported error log if a transcript fails repeatedly.
Provider options
SystemSculpt transcription
Stream audio to the SystemSculpt service with chunked uploads, automatic retries, and a live progress readout in the recorder.
Custom API endpoint
Point to OpenAI, Groq, or any Whisper-compatible endpoint by supplying base URL, API key, and model.
Local Whisper server
Use a LAN Whisper instance (for example
http://localhost:9000/v1/audio/transcriptions) with optional auto-resampling.Checklist
- •Select your preferred microphone in Settings → Recording.
- •Toggle the recorder with ⌘/Ctrl + R to capture audio from Obsidian.
- •Open existing audio via the file context menu → “Transcribe with SystemSculpt”.
- •Decide whether to keep originals and whether transcripts should paste into chat automatically.